跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+479新增论文
+361其中 AI 相关
+63已有论文修订
+93新增 AI 导读

arXiv 最近完成扫描:2026-11-16 01:34 · 全站最近入库:2026-11-16 13:44各信源进度 →

统计口径与数据新鲜度

统计 2026-11-15 16:09 — 2026-11-16 16:09(北京时间) · 点击数字查看对应简报;AI 相关包含在新增论文内。

最近完成检查:2026-11-16 01:34最近发现新增版本:2026-11-16 13:44库内论文最新更新时间:2026-11-14 02:59

每分钟刷新已保存的数据。空检查不代表采集异常;新收录可能包含历史论文。AI 导读按新增版本计数。

23,827 已收录论文19,941 AI 相关6,921 有修订112 HF 社区发现

浏览论文库

时间范围跟随排序:版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常,查看状态 →

找到 23,827 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-16 01:33(北京时间)
版本更新 · v3arXiv:2406.07599Google Research

CTIBench: A Benchmark for Evaluating LLMs in Cyber Threat Intelligence

Md Tanvirul Alam, Dipkamal Bhusal, Le Nguyen, Nidhi Rastogi

原文摘要

Cyber threat intelligence (CTI) is crucial in today's cybersecurity landscape, providing essential insights to understand and mitigate the ever-evolving cyber threats. The recent rise of Large Language Models (LLMs) have shown potential in this domain, but concerns about their reliability, accuracy, and hallucinations persist. While existing benchmarks provide general evaluations of LLMs, there are no benchmarks that address the practical and applied aspects of CTI-specific tasks. To bridge this gap, we introduce CTIBench, a benchmark designed to assess LLMs' performance in CTI applications. CTIBench includes multiple datasets focused on evaluating knowledge acquired by LLMs in the cyber-threat landscape. Our evaluation of several state-of-the-art models on these tasks provides insights into their strengths and weaknesses in CTI contexts, contributing to a better understanding of LLM capabilities in CTI.

cs.CR · cs.AI

新论文 · v1arXiv:2411.04381Google Research

TrajGPT: Controlled Synthetic Trajectory Generation Using a Multitask Transformer-Based Spatiotemporal Model

Shang-Ling Hsu, Emmanuel Tung, John Krumm, Cyrus Shahabi, Khurram Shafique

原文摘要

Human mobility modeling from GPS-trajectories and synthetic trajectory generation are crucial for various applications, such as urban planning, disaster management and epidemiology. Both of these tasks often require filling gaps in a partially specified sequence of visits - a new problem that we call "controlled" synthetic trajectory generation. Existing methods for next-location prediction or synthetic trajectory generation cannot solve this problem as they lack the mechanisms needed to constrain the generated sequences of visits. Moreover, existing approaches (1) frequently treat space and time as independent factors, an assumption that fails to hold true in real-world scenarios, and (2) suffer from challenges in accuracy of temporal prediction as they fail to deal with mixed distributions and the inter-relationships of different modes with latent variables (e.g., day-of-the-week). These limitations become even more pronounced when the task involves filling gaps within sequences instead of solely predicting the next visit. We introduce TrajGPT, a transformer-based, multi-task, joint spatiotemporal generative model to address these issues. Taking inspiration from large language models, TrajGPT poses the problem of controlled trajectory generation as that of text infilling in natural language. TrajGPT integrates the spatial and temporal models in a transformer architecture through a Bayesian probability model that ensures that the gaps in a visit sequence are filled in a spatiotemporally consistent manner. Our experiments on public and private datasets demonstrate that TrajGPT not only excels in controlled synthetic visit generation but also outperforms competing models in next-location prediction tasks - Relatively, TrajGPT achieves a 26-fold improvement in temporal accuracy while retaining more than 98% of spatial accuracy on average.

cs.LG

版本更新 · v2arXiv:2406.10149Google Research

BABILong:用长上下文“草堆寻针”测试大语言模型的推理极限

BABILong: Testing the Limits of LLMs with Long Context Reasoning-in-a-Haystack

Yuri Kuratov, Aydar Bulatov, Petr Anokhin, Ivan Rodkin, Dmitry Sorokin, Artyom Sorokin, Mikhail Burtsev

AI 速读 基于摘要

提出 BABILong 基准,用 20 类推理任务检验大语言模型在超长文档中跨分散事实进行推理的能力。

cs.CL · cs.AI

查看原文摘要

In recent years, the input context sizes of large language models (LLMs) have increased dramatically. However, existing evaluation methods have not kept pace, failing to comprehensively assess the efficiency of models in handling long contexts. To bridge this gap, we introduce the BABILong benchmark, designed to test language models' ability to reason across facts distributed in extremely long documents. BABILong includes a diverse set of 20 reasoning tasks, including fact chaining, simple induction, deduction, counting, and handling lists/sets. These tasks are challenging on their own, and even more demanding when the required facts are scattered across long natural text. Our evaluations show that popular LLMs effectively utilize only 10-20\% of the context and their performance declines sharply with increased reasoning complexity. Among alternatives to in-context reasoning, Retrieval-Augmented Generation methods achieve a modest 60\% accuracy on single-fact question answering, independent of context length. Among context extension methods, the highest performance is demonstrated by recurrent memory transformers after fine-tuning, enabling the processing of lengths up to 50 million tokens. The BABILong benchmark is extendable to any length to support the evaluation of new upcoming models with increased capabilities, and we provide splits up to 10 million token lengths.

版本更新 · v3arXiv:2407.13623Google Research

Scaling Laws with Vocabulary: Larger Models Deserve Larger Vocabularies

Chaofan Tao, Qian Liu, Longxu Dou, Niklas Muennighoff, Zhongwei Wan, Ping Luo, Min Lin, Ngai Wong

原文摘要

Research on scaling large language models (LLMs) has primarily focused on model parameters and training data size, overlooking the role of vocabulary size. We investigate how vocabulary size impacts LLM scaling laws by training models ranging from 33M to 3B parameters on up to 500B characters with various vocabulary configurations. We propose three complementary approaches for predicting the compute-optimal vocabulary size: IsoFLOPs analysis, derivative estimation, and parametric fit of the loss function. Our approaches converge on the conclusion that the optimal vocabulary size depends on the compute budget, with larger models requiring larger vocabularies. Most LLMs, however, use insufficient vocabulary sizes. For example, we predict that the optimal vocabulary size of Llama2-70B should have been at least 216K, 7 times larger than its vocabulary of 32K. We validate our predictions empirically by training models with 3B parameters across different FLOPs budgets. Adopting our predicted optimal vocabulary size consistently improves downstream performance over commonly used vocabulary sizes. By increasing the vocabulary size from the conventional 32K to 43K, we improve performance on ARC-Challenge from 29.1 to 32.0 with the same 2.3e21 FLOPs. Our work highlights the importance of jointly considering tokenization and model scaling for efficient pre-training. The code and demo are available at https://github.com/sail-sg/scaling-with-vocab and https://hf.co/spaces/sail/scaling-with-vocab-demo.

cs.CL · cs.AI

版本更新 · v2arXiv:2402.05120Google Research

More Agents Is All You Need

Junyou Li, Qin Zhang, Yangbin Yu, Qiang Fu, Deheng Ye

原文摘要

We find that, simply via a sampling-and-voting method, the performance of large language models (LLMs) scales with the number of agents instantiated. Also, this method, termed as Agent Forest, is orthogonal to existing complicated methods to further enhance LLMs, while the degree of enhancement is correlated to the task difficulty. We conduct comprehensive experiments on a wide range of LLM benchmarks to verify the presence of our finding, and to study the properties that can facilitate its occurrence. Our code is publicly available at: https://github.com/MoreAgentsIsAllYouNeed/AgentForest

cs.CL · cs.AI · cs.LG

版本更新 · v2arXiv:2410.04587Google Research

Hammer:通过函数掩码实现端侧语言模型的鲁棒函数调用

Hammer: Robust Function-Calling for On-Device Language Models via Function Masking

Qiqiang Lin, Muning Wen, Qiuying Peng, Guanyu Nie, Junwei Liao, Jun Wang, Xiaoyun Mo, Jiamu Zhou 等 12 位作者

AI 速读 基于摘要

提出 Hammer 系列端侧函数调用基础模型,通过增强数据集和函数掩码技术提升对无关函数的敏感性和跨基准泛化能力。

cs.LG · cs.AI · cs.SE

查看原文摘要

Large language models have demonstrated impressive value in performing as autonomous agents when equipped with external tools and API calls. Nonetheless, effectively harnessing their potential for executing complex tasks crucially relies on enhancements in their function calling capabilities. This paper identifies a critical gap in existing function calling models, where performance varies significantly across benchmarks, often due to being misled by specific naming conventions. To address such an issue, we introduce Hammer, a novel family of foundation models specifically engineered for on-device function calling. Hammer employs an augmented dataset that enhances models' sensitivity to irrelevant functions and incorporates function masking techniques to minimize misleading. Our empirical evaluations reveal that Hammer not only outperforms larger models but also demonstrates robust generalization across diverse benchmarks, achieving sota results. Our open source contributions include a specialized dataset for irrelevance detection, a tuning framework for enhanced generalization, and the Hammer models, establishing a new standard for function calling performance.

版本更新 · v3arXiv:2311.08105Google DeepMind

DiLoCo: Distributed Low-Communication Training of Language Models

Arthur Douillard, Qixuan Feng, Andrei A. Rusu, Rachita Chhaparia, Yani Donchev, Adhiguna Kuncoro, Marc'Aurelio Ranzato, Arthur Szlam 等 9 位作者

原文摘要

Large language models (LLM) have become a critical component in many applications of machine learning. However, standard approaches to training LLM require a large number of tightly interconnected accelerators, with devices exchanging gradients and other intermediate states at each optimization step. While it is difficult to build and maintain a single computing cluster hosting many accelerators, it might be easier to find several computing clusters each hosting a smaller number of devices. In this work, we propose a distributed optimization algorithm, Distributed Low-Communication (DiLoCo), that enables training of language models on islands of devices that are poorly connected. The approach is a variant of federated averaging, where the number of inner steps is large, the inner optimizer is AdamW, and the outer optimizer is Nesterov momentum. On the widely used C4 dataset, we show that DiLoCo on 8 workers performs as well as fully synchronous optimization while communicating 500 times less. DiLoCo exhibits great robustness to the data distribution of each worker. It is also robust to resources becoming unavailable over time, and vice versa, it can seamlessly leverage resources that become available during training.

cs.LG · cs.CL

新论文 · v1arXiv:2409.07429Google Research

Agent Workflow Memory

Zora Zhiruo Wang, Jiayuan Mao, Daniel Fried, Graham Neubig

原文摘要

Despite the potential of language model-based agents to solve real-world tasks such as web navigation, current methods still struggle with long-horizon tasks with complex action trajectories. In contrast, humans can flexibly solve complex tasks by learning reusable task workflows from past experiences and using them to guide future actions. To build agents that can similarly benefit from this process, we introduce Agent Workflow Memory (AWM), a method for inducing commonly reused routines, i.e., workflows, and selectively providing workflows to the agent to guide subsequent generations. AWM flexibly applies to both offline and online scenarios, where agents induce workflows from training examples beforehand or from test queries on the fly. We experiment on two major web navigation benchmarks -- Mind2Web and WebArena -- that collectively cover 1000+ tasks from 200+ domains across travel, shopping, and social media, among others. AWM substantially improves the baseline results by 24.6% and 51.1% relative success rate on Mind2Web and WebArena while reducing the number of steps taken to solve WebArena tasks successfully. Furthermore, online AWM robustly generalizes in cross-task, website, and domain evaluations, surpassing baselines from 8.9 to 14.0 absolute points as train-test task distribution gaps widen.

cs.CL

版本更新 · v3arXiv:2402.05070Google Research

A Roadmap to Pluralistic Alignment

Taylor Sorensen, Jared Moore, Jillian Fisher, Mitchell Gordon, Niloofar Mireshghallah, Christopher Michael Rytting, Andre Ye, Liwei Jiang 等 12 位作者

原文摘要

With increased power and prevalence of AI systems, it is ever more critical that AI systems are designed to serve all, i.e., people with diverse values and perspectives. However, aligning models to serve pluralistic human values remains an open research question. In this piece, we propose a roadmap to pluralistic alignment, specifically using language models as a test bed. We identify and formalize three possible ways to define and operationalize pluralism in AI systems: 1) Overton pluralistic models that present a spectrum of reasonable responses; 2) Steerably pluralistic models that can steer to reflect certain perspectives; and 3) Distributionally pluralistic models that are well-calibrated to a given population in distribution. We also formalize and discuss three possible classes of pluralistic benchmarks: 1) Multi-objective benchmarks, 2) Trade-off steerable benchmarks, which incentivize models to steer to arbitrary trade-offs, and 3) Jury-pluralistic benchmarks which explicitly model diverse human ratings. We use this framework to argue that current alignment techniques may be fundamentally limited for pluralistic AI; indeed, we highlight empirical evidence, both from our own experiments and from other work, that standard alignment procedures might reduce distributional pluralism in models, motivating the need for further research on pluralistic alignment.

cs.AI · cs.CL · cs.IR

版本更新 · v2arXiv:2310.06839Berkeley BAIR

LongLLMLingua:通过提示压缩加速并增强长上下文场景中的大语言模型

LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression

Huiqiang Jiang, Qianhui Wu, Xufang Luo, Dongsheng Li, Chin-Yew Lin, Yuqing Yang, Lili Qiu

AI 速读 基于摘要

提出 LongLLMLingua 提示压缩方法,旨在同时缓解长上下文场景下的计算成本高、性能下降和位置偏差三大问题。

cs.CL · cs.LG

查看原文摘要

In long context scenarios, large language models (LLMs) face three main challenges: higher computational cost, performance reduction, and position bias. Research indicates that LLM performance hinges on the density and position of key information in the input prompt. Inspired by these findings, we propose LongLLMLingua for prompt compression towards improving LLMs' perception of the key information to simultaneously address the three challenges. Our extensive evaluation across various long context scenarios demonstrates that LongLLMLingua not only enhances performance but also significantly reduces costs and latency. For instance, in the NaturalQuestions benchmark, LongLLMLingua boosts performance by up to 21.4% with around 4x fewer tokens in GPT-3.5-Turbo, leading to substantial cost savings. It achieves a 94.0% cost reduction in the LooGLE benchmark. Moreover, when compressing prompts of about 10k tokens at ratios of 2x-6x, LongLLMLingua can accelerate end-to-end latency by 1.4x-2.6x. Our code is available at https://aka.ms/LongLLMLingua.

新论文 · v1arXiv:2408.03314Google Research

Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters

Charlie Snell, Jaehoon Lee, Kelvin Xu, Aviral Kumar

原文摘要

Enabling LLMs to improve their outputs by using more test-time computation is a critical step towards building generally self-improving agents that can operate on open-ended natural language. In this paper, we study the scaling of inference-time computation in LLMs, with a focus on answering the question: if an LLM is allowed to use a fixed but non-trivial amount of inference-time compute, how much can it improve its performance on a challenging prompt? Answering this question has implications not only on the achievable performance of LLMs, but also on the future of LLM pretraining and how one should tradeoff inference-time and pre-training compute. Despite its importance, little research attempted to understand the scaling behaviors of various test-time inference methods. Moreover, current work largely provides negative results for a number of these strategies. In this work, we analyze two primary mechanisms to scale test-time computation: (1) searching against dense, process-based verifier reward models; and (2) updating the model's distribution over a response adaptively, given the prompt at test time. We find that in both cases, the effectiveness of different approaches to scaling test-time compute critically varies depending on the difficulty of the prompt. This observation motivates applying a "compute-optimal" scaling strategy, which acts to most effectively allocate test-time compute adaptively per prompt. Using this compute-optimal strategy, we can improve the efficiency of test-time compute scaling by more than 4x compared to a best-of-N baseline. Additionally, in a FLOPs-matched evaluation, we find that on problems where a smaller base model attains somewhat non-trivial success rates, test-time compute can be used to outperform a 14x larger model.

cs.LG · cs.CL

版本更新 · v2arXiv:2405.00823Google Research

WorkBench: a Benchmark Dataset for Agents in a Realistic Workplace Setting

Olly Styles, Sam Miller, Patricio Cerda-Mardini, Tanaya Guha, Victor Sanchez, Bertie Vidgen

原文摘要

We introduce WorkBench: a benchmark dataset for evaluating agents' ability to execute tasks in a workplace setting. WorkBench contains a sandbox environment with five databases, 26 tools, and 690 tasks. These tasks represent common business activities, such as sending emails and scheduling meetings. The tasks in WorkBench are challenging as they require planning, tool selection, and often multiple actions. If a task has been successfully executed, one (or more) of the database values may change. The correct outcome for each task is unique and unambiguous, which allows for robust, automated evaluation. We call this key contribution outcome-centric evaluation. We evaluate five existing ReAct agents on WorkBench, finding they successfully complete as few as 3% of tasks (Llama2-70B), and just 43% for the best-performing (GPT-4). We further find that agents' errors can result in the wrong action being taken, such as an email being sent to the wrong person. WorkBench reveals weaknesses in agents' ability to undertake common business activities, raising questions about their use in high-stakes workplace settings. WorkBench is publicly available as a free resource at https://github.com/olly-styles/WorkBench.

cs.CL · cs.AI · cs.MA

版本更新 · v2arXiv:2406.03482Google Research

QJL: 1-Bit Quantized JL Transform for KV Cache Quantization with Zero Overhead

Amir Zandieh, Majid Daliri, Insu Han

原文摘要

Serving LLMs requires substantial memory due to the storage requirements of Key-Value (KV) embeddings in the KV cache, which grows with sequence length. An effective approach to compress KV cache is quantization. However, traditional quantization methods face significant memory overhead due to the need to store quantization constants (at least a zero point and a scale) in full precision per data block. Depending on the block size, this overhead can add 1 or 2 bits per quantized number. We introduce QJL, a new quantization approach that consists of a Johnson-Lindenstrauss (JL) transform followed by sign-bit quantization. In contrast to existing methods, QJL eliminates memory overheads by removing the need for storing quantization constants. We propose an asymmetric estimator for the inner product of two vectors and demonstrate that applying QJL to one vector and a standard JL transform without quantization to the other provides an unbiased estimator with minimal distortion. We have developed an efficient implementation of the QJL sketch and its corresponding inner product estimator, incorporating a lightweight CUDA kernel for optimized computation. When applied across various LLMs and NLP tasks to quantize the KV cache to only 3 bits, QJL demonstrates a more than fivefold reduction in KV cache memory usage without compromising accuracy, all while achieving faster runtime. Codes are available at \url{https://github.com/amirzandieh/QJL}.

cs.LG · cs.AI · cs.CL · cs.PF

版本更新 · v2arXiv:2311.03658Berkeley BAIR

线性表示假设与大语言模型的几何

The Linear Representation Hypothesis and the Geometry of Large Language Models

Kiho Park, Yo Joong Choe, Victor Veitch

AI 速读 基于摘要

该论文形式化了“线性表示假设”,提出因果内积来统一线性探测和模型引导,并在LLaMA-2上验证概念线性表示的存在。

cs.CL · cs.AI · cs.LG · stat.ML

查看原文摘要

Informally, the 'linear representation hypothesis' is the idea that high-level concepts are represented linearly as directions in some representation space. In this paper, we address two closely related questions: What does "linear representation" actually mean? And, how do we make sense of geometric notions (e.g., cosine similarity or projection) in the representation space? To answer these, we use the language of counterfactuals to give two formalizations of "linear representation", one in the output (word) representation space, and one in the input (sentence) space. We then prove these connect to linear probing and model steering, respectively. To make sense of geometric notions, we use the formalization to identify a particular (non-Euclidean) inner product that respects language structure in a sense we make precise. Using this causal inner product, we show how to unify all notions of linear representation. In particular, this allows the construction of probes and steering vectors using counterfactual pairs. Experiments with LLaMA-2 demonstrate the existence of linear representations of concepts, the connection to interpretation and control, and the fundamental role of the choice of inner product.

版本更新 · v2arXiv:2310.11324Google Research

Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Melanie Sclar, Yejin Choi, Yulia Tsvetkov, Alane Suhr

原文摘要

As large language models (LLMs) are adopted as a fundamental component of language technologies, it is crucial to accurately characterize their performance. Because choices in prompt design can strongly influence model behavior, this design process is critical in effectively using any modern pre-trained generative language model. In this work, we focus on LLM sensitivity to a quintessential class of meaning-preserving design choices: prompt formatting. We find that several widely used open-source LLMs are extremely sensitive to subtle changes in prompt formatting in few-shot settings, with performance differences of up to 76 accuracy points when evaluated using LLaMA-2-13B. Sensitivity remains even when increasing model size, the number of few-shot examples, or performing instruction tuning. Our analysis suggests that work evaluating LLMs with prompting-based methods would benefit from reporting a range of performance across plausible prompt formats, instead of the currently-standard practice of reporting performance on a single format. We also show that format performance only weakly correlates between models, which puts into question the methodological validity of comparing models with an arbitrarily chosen, fixed prompt format. To facilitate systematic analysis we propose FormatSpread, an algorithm that rapidly evaluates a sampled set of plausible prompt formats for a given task, and reports the interval of expected performance without accessing model weights. Furthermore, we present a suite of analyses that characterize the nature of this sensitivity, including exploring the influence of particular atomic perturbations and the internal representation of particular formats.

cs.CL · cs.AI · cs.LG

新论文 · v1arXiv:2406.07496Google Research

TextGrad:通过文本进行自动“微分”

TextGrad: Automatic "Differentiation" via Text

Mert Yuksekgonul, Federico Bianchi, Joseph Boen, Sheng Liu, Zhi Huang, Carlos Guestrin, James Zou

AI 速读 基于摘要

TextGrad 利用 LLM 提供的文本反馈对复合 AI 系统进行类似自动微分的优化,并在多种任务上展示了效果。

cs.CL · cs.AI · cs.LG

查看原文摘要

AI is undergoing a paradigm shift, with breakthroughs achieved by systems orchestrating multiple large language models (LLMs) and other complex components. As a result, developing principled and automated optimization methods for compound AI systems is one of the most important new challenges. Neural networks faced a similar challenge in its early days until backpropagation and automatic differentiation transformed the field by making optimization turn-key. Inspired by this, we introduce TextGrad, a powerful framework performing automatic ``differentiation'' via text. TextGrad backpropagates textual feedback provided by LLMs to improve individual components of a compound AI system. In our framework, LLMs provide rich, general, natural language suggestions to optimize variables in computation graphs, ranging from code snippets to molecular structures. TextGrad follows PyTorch's syntax and abstraction and is flexible and easy-to-use. It works out-of-the-box for a variety of tasks, where the users only provide the objective function without tuning components or prompts of the framework. We showcase TextGrad's effectiveness and generality across a diverse range of applications, from question answering and molecule optimization to radiotherapy treatment planning. Without modifying the framework, TextGrad improves the zero-shot accuracy of GPT-4o in Google-Proof Question Answering from $51\%$ to $55\%$, yields $20\%$ relative performance gain in optimizing LeetCode-Hard coding problem solutions, improves prompts for reasoning, designs new druglike small molecules with desirable in silico binding, and designs radiation oncology treatment plans with high specificity. TextGrad lays a foundation to accelerate the development of the next-generation of AI systems.

新论文 · v1arXiv:2405.21060Google Research

Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality

Tri Dao, Albert Gu

原文摘要

While Transformers have been the main architecture behind deep learning's success in language modeling, state-space models (SSMs) such as Mamba have recently been shown to match or outperform Transformers at small to medium scale. We show that these families of models are actually quite closely related, and develop a rich framework of theoretical connections between SSMs and variants of attention, connected through various decompositions of a well-studied class of structured semiseparable matrices. Our state space duality (SSD) framework allows us to design a new architecture (Mamba-2) whose core layer is an a refinement of Mamba's selective SSM that is 2-8X faster, while continuing to be competitive with Transformers on language modeling.

cs.LG

版本更新 · v4arXiv:2309.12288Google Research

The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A"

Lukas Berglund, Meg Tong, Max Kaufmann, Mikita Balesni, Asa Cooper Stickland, Tomasz Korbak, Owain Evans

原文摘要

We expose a surprising failure of generalization in auto-regressive large language models (LLMs). If a model is trained on a sentence of the form "A is B", it will not automatically generalize to the reverse direction "B is A". This is the Reversal Curse. For instance, if a model is trained on "Valentina Tereshkova was the first woman to travel to space", it will not automatically be able to answer the question, "Who was the first woman to travel to space?". Moreover, the likelihood of the correct answer ("Valentina Tershkova") will not be higher than for a random name. Thus, models do not generalize a prevalent pattern in their training set: if "A is B" occurs, "B is A" is more likely to occur. It is worth noting, however, that if "A is B" appears in-context, models can deduce the reverse relationship. We provide evidence for the Reversal Curse by finetuning GPT-3 and Llama-1 on fictitious statements such as "Uriah Hawthorne is the composer of Abyssal Melodies" and showing that they fail to correctly answer "Who composed Abyssal Melodies?". The Reversal Curse is robust across model sizes and model families and is not alleviated by data augmentation. We also evaluate ChatGPT (GPT-3.5 and GPT-4) on questions about real-world celebrities, such as "Who is Tom Cruise's mother? [A: Mary Lee Pfeiffer]" and the reverse "Who is Mary Lee Pfeiffer's son?". GPT-4 correctly answers questions like the former 79% of the time, compared to 33% for the latter. Code available at: https://github.com/lukasberglund/reversal_curse.

cs.CL · cs.AI · cs.LG

新论文 · v1arXiv:2406.18554Google Research

Planted: a dataset for planted forest identification from multi-satellite time series

Luis Miguel Pazos-Outón, Cristina Nader Vasconcelos, Anton Raichuk, Anurag Arnab, Dan Morris, Maxim Neumann

原文摘要

Protecting and restoring forest ecosystems is critical for biodiversity conservation and carbon sequestration. Forest monitoring on a global scale is essential for prioritizing and assessing conservation efforts. Satellite-based remote sensing is the only viable solution for providing global coverage, but to date, large-scale forest monitoring is limited to single modalities and single time points. In this paper, we present a dataset consisting of data from five public satellites for recognizing forest plantations and planted tree species across the globe. Each satellite modality consists of a multi-year time series. The dataset, named \PlantD, includes over 2M examples of 64 tree label classes (46 genera and 40 species), distributed among 41 countries. This dataset is released to foster research in forest monitoring using multimodal, multi-scale, multi-temporal data sources. Additionally, we present initial baseline results and evaluate modality fusion and data augmentation approaches for this dataset.

cs.CV · cs.LG

版本更新 · v2arXiv:2404.16436Google Research

Leveraging tropical reef, bird and unrelated sounds for superior transfer learning in marine bioacoustics

Ben Williams, Bart van Merriënboer, Vincent Dumoulin, Jenny Hamer, Eleni Triantafillou, Abram B. Fleishman, Matthew McKown, Jill E. Munger 等 15 位作者

原文摘要

Machine learning has the potential to revolutionize passive acoustic monitoring (PAM) for ecological assessments. However, high annotation and compute costs limit the field's efficacy. Generalizable pretrained networks can overcome these costs, but high-quality pretraining requires vast annotated libraries, limiting its current applicability primarily to bird taxa. Here, we identify the optimum pretraining strategy for a data-deficient domain using coral reef bioacoustics. We assemble ReefSet, a large annotated library of reef sounds, though modest compared to bird libraries at 2% of the sample count. Through testing few-shot transfer learning performance, we observe that pretraining on bird audio provides notably superior generalizability compared to pretraining on ReefSet or unrelated audio alone. However, our key findings show that cross-domain mixing which leverages bird, reef and unrelated audio during pretraining maximizes reef generalizability. SurfPerch, our pretrained network, provides a strong foundation for automated analysis of marine PAM data with minimal annotation and compute costs.

cs.SD · cs.AI · cs.LG · eess.AS

新论文 · v1arXiv:2404.19737Google Research

Better & Faster Large Language Models via Multi-token Prediction

Fabian Gloeckle, Badr Youbi Idrissi, Baptiste Rozière, David Lopez-Paz, Gabriel Synnaeve

原文摘要

Large language models such as GPT and Llama are trained with a next-token prediction loss. In this work, we suggest that training language models to predict multiple future tokens at once results in higher sample efficiency. More specifically, at each position in the training corpus, we ask the model to predict the following n tokens using n independent output heads, operating on top of a shared model trunk. Considering multi-token prediction as an auxiliary training task, we measure improved downstream capabilities with no overhead in training time for both code and natural language models. The method is increasingly useful for larger model sizes, and keeps its appeal when training for multiple epochs. Gains are especially pronounced on generative benchmarks like coding, where our models consistently outperform strong baselines by several percentage points. Our 13B parameter models solves 12 % more problems on HumanEval and 17 % more on MBPP than comparable next-token models. Experiments on small algorithmic tasks demonstrate that multi-token prediction is favorable for the development of induction heads and algorithmic reasoning capabilities. As an additional benefit, models trained with 4-token prediction are up to 3 times faster at inference, even with large batch sizes.

cs.CL

新论文 · v1arXiv:2404.15058Google DeepMind

A Mechanism-Based Approach to Mitigating Harms from Persuasive Generative AI

Seliem El-Sayed, Canfer Akbulut, Amanda McCroskery, Geoff Keeling, Zachary Kenton, Zaria Jalan, Nahema Marchal, Arianna Manzini 等 20 位作者

原文摘要

Recent generative AI systems have demonstrated more advanced persuasive capabilities and are increasingly permeating areas of life where they can influence decision-making. Generative AI presents a new risk profile of persuasion due the opportunity for reciprocal exchange and prolonged interactions. This has led to growing concerns about harms from AI persuasion and how they can be mitigated, highlighting the need for a systematic study of AI persuasion. The current definitions of AI persuasion are unclear and related harms are insufficiently studied. Existing harm mitigation approaches prioritise harms from the outcome of persuasion over harms from the process of persuasion. In this paper, we lay the groundwork for the systematic study of AI persuasion. We first put forward definitions of persuasive generative AI. We distinguish between rationally persuasive generative AI, which relies on providing relevant facts, sound reasoning, or other forms of trustworthy evidence, and manipulative generative AI, which relies on taking advantage of cognitive biases and heuristics or misrepresenting information. We also put forward a map of harms from AI persuasion, including definitions and examples of economic, physical, environmental, psychological, sociocultural, political, privacy, and autonomy harm. We then introduce a map of mechanisms that contribute to harmful persuasion. Lastly, we provide an overview of approaches that can be used to mitigate against process harms of persuasion, including prompt engineering for manipulation classification and red teaming. Future work will operationalise these mitigations and study the interaction between different types of mechanisms of persuasion.

cs.CY · cs.AI

版本更新 · v3arXiv:2310.02226Google Research

Think before you speak: Training Language Models With Pause Tokens

Sachin Goyal, Ziwei Ji, Ankit Singh Rawat, Aditya Krishna Menon, Sanjiv Kumar, Vaishnavh Nagarajan

原文摘要

Language models generate responses by producing a series of tokens in immediate succession: the $(K+1)^{th}$ token is an outcome of manipulating $K$ hidden vectors per layer, one vector per preceding token. What if instead we were to let the model manipulate say, $K+10$ hidden vectors, before it outputs the $(K+1)^{th}$ token? We operationalize this idea by performing training and inference on language models with a (learnable) $\textit{pause}$ token, a sequence of which is appended to the input prefix. We then delay extracting the model's outputs until the last pause token is seen, thereby allowing the model to process extra computation before committing to an answer. We empirically evaluate $\textit{pause-training}$ on decoder-only models of 1B and 130M parameters with causal pretraining on C4, and on downstream tasks covering reasoning, question-answering, general understanding and fact recall. Our main finding is that inference-time delays show gains when the model is both pre-trained and finetuned with delays. For the 1B model, we witness gains on 8 of 9 tasks, most prominently, a gain of $18\%$ EM score on the QA task of SQuAD, $8\%$ on CommonSenseQA and $1\%$ accuracy on the reasoning task of GSM8k. Our work raises a range of conceptual and practical future research questions on making delayed next-token prediction a widely applicable new paradigm.

cs.CL · cs.AI · cs.LG

版本更新 · v4arXiv:2307.13854Google Research

WebArena: A Realistic Web Environment for Building Autonomous Agents

Shuyan Zhou, Frank F. Xu, Hao Zhu, Xuhui Zhou, Robert Lo, Abishek Sridhar, Xianyi Cheng, Tianyue Ou 等 12 位作者

原文摘要

With advances in generative AI, there is now potential for autonomous agents to manage daily tasks via natural language commands. However, current agents are primarily created and tested in simplified synthetic environments, leading to a disconnect with real-world scenarios. In this paper, we build an environment for language-guided agents that is highly realistic and reproducible. Specifically, we focus on agents that perform tasks on the web, and create an environment with fully functional websites from four common domains: e-commerce, social forum discussions, collaborative software development, and content management. Our environment is enriched with tools (e.g., a map) and external knowledge bases (e.g., user manuals) to encourage human-like task-solving. Building upon our environment, we release a set of benchmark tasks focusing on evaluating the functional correctness of task completions. The tasks in our benchmark are diverse, long-horizon, and designed to emulate tasks that humans routinely perform on the internet. We experiment with several baseline agents, integrating recent techniques such as reasoning before acting. The results demonstrate that solving complex tasks is challenging: our best GPT-4-based agent only achieves an end-to-end task success rate of 14.41%, significantly lower than the human performance of 78.24%. These results highlight the need for further development of robust agents, that current state-of-the-art large language models are far from perfect performance in these real-life tasks, and that WebArena can be used to measure such progress.

cs.AI · cs.CL · cs.LG

版本更新 · v8arXiv:1904.07272Google Research

多臂老虎机导论

Introduction to Multi-Armed Bandits

Aleksandrs Slivkins

AI 速读 基于摘要

一本以教科书方式系统介绍多臂老虎机(multi-armed bandits)的入门著作,覆盖IID奖励、对抗性奖励、上下文老虎机及与经济学相关的扩展。

cs.LG · cs.AI · cs.DS · stat.ML

查看原文摘要

Multi-armed bandits a simple but very powerful framework for algorithms that make decisions over time under uncertainty. An enormous body of work has accumulated over the years, covered in several books and surveys. This book provides a more introductory, textbook-like treatment of the subject. Each chapter tackles a particular line of work, providing a self-contained, teachable technical introduction and a brief review of the further developments; many of the chapters conclude with exercises. The book is structured as follows. The first four chapters are on IID rewards, from the basic model to impossibility results to Bayesian priors to Lipschitz rewards. The next three chapters cover adversarial rewards, from the full-feedback version to adversarial bandits to extensions with linear rewards and combinatorially structured actions. Chapter 8 is on contextual bandits, a middle ground between IID and adversarial bandits in which the change in reward distributions is completely explained by observable contexts. The last three chapters cover connections to economics, from learning in repeated games to bandits with supply/budget constraints to exploration in the presence of incentives. The appendix provides sufficient background on concentration and KL-divergence. The chapters on "bandits with similarity information", "bandits with knapsacks" and "bandits and agents" can also be consumed as standalone surveys on the respective topics.

新论文 · v1arXiv:2403.17660Google DeepMind

CANOS: A Fast and Scalable Neural AC-OPF Solver Robust To N-1 Perturbations

Luis Piloto, Sofia Liguori, Sephora Madjiheurem, Miha Zgubic, Sean Lovett, Hamish Tomlinson, Sophie Elster, Chris Apps 等 9 位作者

原文摘要

Optimal Power Flow (OPF) refers to a wide range of related optimization problems with the goal of operating power systems efficiently and securely. In the simplest setting, OPF determines how much power to generate in order to minimize costs while meeting demand for power and satisfying physical and operational constraints. In even the simplest case, power grid operators use approximations of the AC-OPF problem because solving the exact problem is prohibitively slow with state-of-the-art solvers. These approximations sacrifice accuracy and operational feasibility in favor of speed. This trade-off leads to costly "uplift payments" and increased carbon emissions, especially for large power grids. In the present work, we train a deep learning system (CANOS) to predict near-optimal solutions (within 1% of the true AC-OPF cost) without compromising speed (running in as little as 33--65 ms). Importantly, CANOS scales to realistic grid sizes with promising empirical results on grids containing as many as 10,000 buses. Finally, because CANOS is a Graph Neural Network, it is robust to changes in topology. We show that CANOS is accurate across N-1 topological perturbations of a base grid typically used in security-constrained analysis. This paves the way for more efficient optimization of more complex OPF problems which alter grid connectivity such as unit commitment, topology optimization and security-constrained OPF.

cs.LG

新论文 · v1arXiv:2403.02522Google Research

HeAR——健康声学表征

HeAR -- Health Acoustic Representations

Sebastien Baur, Zaid Nabulsi, Wei-Hung Weng, Jake Garrison, Louis Blankemeier, Sam Fishman, Christina Chen, Sujay Kakarmath 等 18 位作者

AI 速读 基于摘要

作者提出基于掩码自编码器、在3.13亿段两秒音频片段上自监督训练的健康声学表征模型 HeAR,并通过线性探针在33项健康声学任务上评估其嵌入质量。

cs.LG · cs.AI

查看原文摘要

Health acoustic sounds such as coughs and breaths are known to contain useful health signals with significant potential for monitoring health and disease, yet are underexplored in the medical machine learning community. The existing deep learning systems for health acoustics are often narrowly trained and evaluated on a single task, which is limited by data and may hinder generalization to other tasks. To mitigate these gaps, we develop HeAR, a scalable self-supervised learning-based deep learning system using masked autoencoders trained on a large dataset of 313 million two-second long audio clips. Through linear probes, we establish HeAR as a state-of-the-art health audio embedding model on a benchmark of 33 health acoustic tasks across 6 datasets. By introducing this work, we hope to enable and accelerate further health acoustics research.

版本更新 · v2arXiv:2310.08560Berkeley BAIR

MemGPT:迈向将大语言模型作为操作系统

MemGPT: Towards LLMs as Operating Systems

Charles Packer, Sarah Wooders, Kevin Lin, Vivian Fang, Shishir G. Patil, Ion Stoica, Joseph E. Gonzalez

AI 速读 基于摘要

受操作系统分层内存启发,提出虚拟上下文管理,让LLM在有限上下文窗口内处理超长文档与多轮长期对话。

cs.AI

查看原文摘要

Large language models (LLMs) have revolutionized AI, but are constrained by limited context windows, hindering their utility in tasks like extended conversations and document analysis. To enable using context beyond limited context windows, we propose virtual context management, a technique drawing inspiration from hierarchical memory systems in traditional operating systems that provide the appearance of large memory resources through data movement between fast and slow memory. Using this technique, we introduce MemGPT (Memory-GPT), a system that intelligently manages different memory tiers in order to effectively provide extended context within the LLM's limited context window, and utilizes interrupts to manage control flow between itself and the user. We evaluate our OS-inspired design in two domains where the limited context windows of modern LLMs severely handicaps their performance: document analysis, where MemGPT is able to analyze large documents that far exceed the underlying LLM's context window, and multi-session chat, where MemGPT can create conversational agents that remember, reflect, and evolve dynamically through long-term interactions with their users. We release MemGPT code and data for our experiments at https://memgpt.ai.

版本更新 · v3arXiv:2306.07863Google Research

Synapse: Trajectory-as-Exemplar Prompting with Memory for Computer Control

Longtao Zheng, Rundong Wang, Xinrun Wang, Bo An

原文摘要

Building agents with large language models (LLMs) for computer control is a burgeoning research area, where the agent receives computer states and performs actions to complete complex tasks. Previous computer agents have demonstrated the benefits of in-context learning (ICL); however, their performance is hindered by several issues. First, the limited context length of LLMs and complex computer states restrict the number of exemplars, as a single webpage can consume the entire context. Second, the exemplars in current methods, such as high-level plans and multi-choice questions, cannot represent complete trajectories, leading to suboptimal performance in long-horizon tasks. Third, existing computer agents rely on task-specific exemplars and overlook the similarity among tasks, resulting in poor generalization to novel tasks. To address these challenges, we introduce Synapse, a computer agent featuring three key components: i) state abstraction, which filters out task-irrelevant information from raw states, allowing more exemplars within the limited context, ii) trajectory-as-exemplar prompting, which prompts the LLM with complete trajectories of the abstracted states and actions to improve multi-step decision-making, and iii) exemplar memory, which stores the embeddings of exemplars and retrieves them via similarity search for generalization to novel tasks. We evaluate Synapse on MiniWoB++, a standard task suite, and Mind2Web, a real-world website benchmark. In MiniWoB++, Synapse achieves a 99.2% average success rate (a 10% relative improvement) across 64 tasks using demonstrations from only 48 tasks. Notably, Synapse is the first ICL method to solve the book-flight task in MiniWoB++. Synapse also exhibits a 56% relative improvement in average step success rate over the previous state-of-the-art prompting scheme in Mind2Web.

cs.AI

版本更新 · v4arXiv:2306.05685Google Research

Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena

Lianmin Zheng, Wei-Lin Chiang, Ying Sheng, Siyuan Zhuang, Zhanghao Wu, Yonghao Zhuang, Zi Lin, Zhuohan Li 等 13 位作者

原文摘要

Evaluating large language model (LLM) based chat assistants is challenging due to their broad capabilities and the inadequacy of existing benchmarks in measuring human preferences. To address this, we explore using strong LLMs as judges to evaluate these models on more open-ended questions. We examine the usage and limitations of LLM-as-a-judge, including position, verbosity, and self-enhancement biases, as well as limited reasoning ability, and propose solutions to mitigate some of them. We then verify the agreement between LLM judges and human preferences by introducing two benchmarks: MT-bench, a multi-turn question set; and Chatbot Arena, a crowdsourced battle platform. Our results reveal that strong LLM judges like GPT-4 can match both controlled and crowdsourced human preferences well, achieving over 80% agreement, the same level of agreement between humans. Hence, LLM-as-a-judge is a scalable and explainable way to approximate human preferences, which are otherwise very expensive to obtain. Additionally, we show our benchmark and traditional benchmarks complement each other by evaluating several variants of LLaMA and Vicuna. The MT-bench questions, 3K expert votes, and 30K conversations with human preferences are publicly available at https://github.com/lm-sys/FastChat/tree/main/fastchat/llm_judge.

cs.CL · cs.AI