FARMS: A Verifiable Foundation for Automated Computational Science
Di Wu, Ling Liang, Haizhao Yang
AI 速览：作者提出 FARMS，将计算数学知识转化为可供 AI 解释与复用、并带有显式保证的“计算知识”基础。
Automated computational science could accelerate discovery by selecting, adapting and developing numerical methods. This prospect requires mathematical knowledge that AI systems can interpret and reuse with explicit guarantees. Here we present FARMS, a faithful and efficient foundation that transforms computational mathematics into AI-ready computing knowledge. FARMS connects formal statements to source context, algorithmic meaning and quantitative guarantees through source preparation, reusable representations and semantic review. Across 171 targets in randomized numerical linear algebra and numerical partial differential equations, 157 were accepted by the pipeline, with mean estimated costs of US \$0.85-2.29 per target across sources. Lean-checked implications from explicit source premises connect selected statements to computational skills, illustrated by a heat-flow solve and wave-response compression. FARMS therefore supports an affordable, reusable knowledge foundation for trustworthy automated computational science.
Smartphone agents increasingly work as teams, in which a large planner directs parallel workers across long sessions. Running such a team on the device requires 200B-class models and contexts that exceed phone DRAM many times over, yet existing tiers treat flash as storage: UFS starves per-token weight streaming, and mobile High-Bandwidth Flash (HBF) needs a redesigned SoC and cannot absorb continuous KV writes. We show that a non-volatile memory can join an unmodified LPDDR6 bus as a plain rank only if its access latency fits the DRAM timing window, a condition no NAND tier meets. We present NORmal, to our knowledge the first main-memory architecture for 3D ferroelectric NOR flash. We have fabricated and experimentally characterized back-end-of-line (BEOL) 3D FeNOR arrays that co-integrate dense 3-bit MLC and fast, high-endurance in-place-writable SLC with sub-7.5 ns sensing. NORmal turns these co-fabricated arrays into a byte-addressable, deterministic-timing load/store rank on an unmodified LPDDR6 interface through an under-array DRAM-emulation bridge, staggered bank reads with zero-cycle weight swizzling, and posted SLC writes. Across this rank and DRAM, NORmal places agent state by mutability and lifetime rather than by hotness, serving 200B-class models and persistent planner contexts in place while dynamically partitioning subchannels across agent phases. In serving-level simulation on production agent traces, NORmal is 8.9$\times$--28.0$\times$ faster than UFS offloading, within 0.4% of an unlimited-DRAM ideal, and 2.8$\times$--6.3$\times$ faster than HBF on sessions beyond 256K tokens, with 8.1$\times$--17.8$\times$ less memory energy per token.
Huanyue Liao, Seok Min Lim, Yan Ling Lim, Shi Min Cheng, Kellin Pelrine, Chen Hui Ong
AI companion chatbots are increasingly used by vulnerable individuals, including adolescents in suicidal crisis, for emotional support. Existing safety evaluations focus on base models, leaving gaps in product-level assessment, crisis-stage sensitivity, and comparisons between companion apps and general-purpose LLMs. We introduce MIRROR-Eval (Multi-turn Interaction Risk Review: Observing suicidal-crisis Responses), a dataset of 960 annotated 20-turn conversations across eight deployed platform configurations, six clinically grounded personas, and two crisis stages: ideation and explicit planning. An LLM-as-a-Judge pipeline applies an expert-reviewed rubric covering user risk severity, chatbot risk awareness, and intervention behavior. We observe a three-tier harm structure: companion apps (Character.AI and Replika) and Grok 4.3 form a high-harm tier; Gemini 3.1 Pro is mid-range; GPT-5.5 and Claude Sonnet 5 show substantially lower harm. At planning, companion apps show increased glorification and normalisation, advancement toward harmful action, and harmful methods and instructions. Crisis recognition and empathetic language do not ensure safe responses. These findings highlight the need for product-level safety evaluation across crisis stages. Dataset and code: https://huggingface.co/datasets/imda-biztech/MIRROR-Eval. Warning: this paper includes examples that may be offensive or harmful.
Pratik Jawahar, Riccardo Maggioni, Jonas Petersen, Matteo Cozzi, Gian-Alessandro Lombardi, Marek Gajewski, Camilla Mazzoleni, Federico Martelli
Test-time compute mechanisms, such as retries, confidence-based escalation and non-local routing, are conventionally deployed as black-box additions to trained models. They typically add forward passes or halting heads, but give no structural account of what the extra compute buys or what it costs against the model's stability guarantees. We therefore propose a theoretical and empirical framework for test-time compute on a Latent Dynamics Model used as the memory. When an encoder's latent state $(q,p)$ is advanced by a damped symplectic (velocity-Verlet) step of a learned Hamiltonian, every mechanism that expands access has an exact phase-volume Jacobian, a bounded energy change and an exact latch-transport law. We split reachability failures into escape failures and reach failures. A Lorentz squeeze resolves escape failures by injecting bounded, re-absorbable energy. A gated canonical translation (a one-step channel across $C_T$) resolves reach failures at $\detJ=1$ exactly. We verify this certificate stack on a designed analytic testbed. Reaching just beyond $C_T$ with the squeeze requires energy that grows quadratically in the excess distance. The gated channel's energy cost equals the potential difference between its endpoints, which is zero on the matched channel measured here, and so does not grow with distance in this testbed. An untrained state-replacing map annihilates phase volume and erases stored charge, while the gated channel transports it. On a learned physics-structured memory, we show calibrated compute rationing and evaluate the scaling limits of non-local routing against a physics-free baseline. The main contribution is the formalization and verification of the certificate stack, not benchmark performance.
Mercy Muchai, Kevin Chege, Nick Mumero Mwangi, Samuel Chege Maina, Felermino Ali, Elizabeth Ankrah, Ignatius Ezeani
Despite recent advancements in ASR, identifying effective architectures, fine-tuning approaches, and data adaptation strategies for low-resource languages remains challenging. We present a systematic comparison across five low-resource African languages and Swahili as a mid-resource contrast, fine-tuning three models from distinct architectures: Phi-4-multimodal-instruct, Whisper-large-v3-turbo, and MMS-1B-all. We analyze data sufficiency, monolingual versus multilingual adaptation, domain fine-tuning, and language-adapter transfer. Phi-4 achieves the best overall accuracy, MMS shows comparable CER, while Whisper exhibits high CER, consistent with known hallucinations and repetition loops. Performance saturates at different data scales, offering practical data-efficiency targets, while typological complexity consistently shapes error rates. Domain fine-tuning benefits Phi-4 and Whisper but degrades MMS, revealing limitations of adapter-based adaptation. Proxy language adapters outperform training MMS adapters from scratch.
Protecting Internet services from attacks such as TLS/HTTP floods requires rate limiting, yet identifying users to enforce these limits can compromise their privacy. Anonymous rate limiting promises to reconcile these goals, but existing schemes either struggle to scale or assume that services and authorities do not collude. We present STAR, which uses server-side trusted execution environments (TEEs) to overcome these limitations. By enabling lightweight cryptographic operations, TEEs make authentication efficient, but introduce a privacy challenge: malicious services can observe memory-access patterns to infer user secrets. We address this threat through countermeasures against secret-dependent memory accesses and assess our implementation using dynamic analysis. To extend these efficiency gains across servers, we also design a secure sharding mechanism that distributes client requests. We demonstrate that strong privacy guarantees can coexist with efficient authentication at scale; STAR processes authentication requests in tens of microseconds and handles approximately 13.9K requests per second per CPU core.
Vincent Herfeld, Eva Coupet{é}, Julien Mairal, Jean Ponce
Continuous space-time video super-resolution produces a high-resolution, highframe-rate video from a low-resolution, low-frame-rate one at arbitrary spatial scales and temporal instants. Classical spatial multi-frame super-resolution has shown that detail beyond a single frame's sampling limit can be recovered by aligning complementary observations with sub-pixel precision and accumulating them on a finer grid. Existing learning-based methods largely depart from this principle: some align and fuse frames only at low resolution before regressing a continuous high-resolution representation, while others interpolate each frame to the output resolution before splatting. In both cases, the per-frame samples are resampled before fusion, so their sub-pixel positions are lost before frames are combined. Restoring this principle in a learned continuous model raises two challenges: estimating sub-pixel motion at unobserved times, and handling holes and occlusions when splatting a coarse grid onto a finer one. We address the first by predicting per-pixel continuous trajectories that refine linear optical-flow paths with smooth residual motion, using features integrated over the full video sequence. We address the second by directly splatting consecutive low-resolution features in a learned latent space onto a high-resolution grid at their predicted sub-pixel positions with predicted visibility weights, before a decoder resolves remaining ambiguities. This makes temporal interpolation and multi-frame superresolution a single operation. Our method improves both reconstruction fidelity and perceptual quality on multiple standard benchmarks over the state of the art, while running up to an order of magnitude faster.
Meiling Li, Pietro Bongini, Benedetta Tondi, Mauro Barni
Synthetic image attribution aims at identifying the generator responsible for a given AI-generated image. Training-free reference-based attribution methods are easily scalable, since newly emerging generators can be incorporated by adding source-specific references rather than retraining a task-specific classifier. Their performance depends on two coupled factors: the representation space used for comparison and the way source-specific references are constructed. However, the interaction between these two factors remains largely unexplored. In this paper, we provide a controlled analysis of this interaction using references and off-the-shelf pretrained representations. We study representations extracted from different layers of CLIP and DINOv2, along with three reference selection strategies with varying semantic constraints: arbitrary, semantically aligned, and resynthesis-based references. Our results show that attribution accuracy generally peaks at intermediate representation levels, indicating that source-discriminative cues are more accessible before strong semantic abstraction dominates. We further show that intermediate representations are not completely semantically neutral, making reference selection critical: semantically constrained references reduce query-reference mismatch and improve attribution, especially under limited reference budgets. Resynthesis is useful in low-reference regimes, while semantically aligned references provide a better accuracy-cost trade-off when a moderate-sized reference pool is available. Our findings show that training-free reference-based attribution should be understood as the interaction between where images are compared, how the reference set is constructed, and how many references are available. Code and datasets are available at https://github.com/meiling-fdu/RefPrint.
Gromov--Wasserstein optimal transport (GWOT) aligns metric measure spaces by matching their within-domain relational structures, but large-scale GWOT remains challenging because its objective is nonconvex and projection onto the transport polytope is often solved only approximately in practice. This leads to a gap between practical projected-gradient implementations and convergence theory, which typically assumes exact projections. For squared-loss GWOT, we propose an inexact projected-gradient framework with a verifiable feasibility-residual-based inexact condition for the projection subproblem. This condition is directly computable and avoids unknown quantities such as the exact projection point. Under this implementable condition, we prove subsequential convergence to stationary points and, with a mild tolerance-decay condition, convergence of the whole sequence. The resulting method retains the simplicity and sparsity of projected-gradient schemes while providing rigorous convergence guarantees, turning projected-gradient methods into a principled and scalable approach for GWOT with provable reliability.
Robot tasks require grounding spatial language in physical scenes, but task success alone cannot establish whether spatial instructions are followed. We present BEHAVIOR-Spatial, a benchmark built on BEHAVIOR-1K that measures spatial question answering, point-based target grounding, and robot action to examine how VLM spatial understanding relates to VLA behavior. It comprises 3,256 spatial questions across 49 activities, 1,240 grounding queries across 14 manipulation tasks, and action evaluations covering those 14 tasks and 10 navigation tasks. Our manipulation protocol evaluates held-out configurations and instruction following when the requested target changes within a fixed training layout. The baseline achieves 41.6% on held-out configurations but only 16.1% under changed instructions. VLM adaptation and robot-data pretraining provide limited improvements, whereas oracle visual target cues raise these rates to 60.3% and 38.0%, respectively. Perception evaluations reveal policy-dependent correlations between VLM question-answering and grounding accuracy and VLA manipulation performance. Together, these findings motivate evaluating spatial instruction following alongside task completion and examining when spatial perception performance translates into robot behavior. Project website: https://arielchen07.github.io/behavior-spatial/.
Generative AI (GenAI) makes open source software (OSS) contributions cheaper to produce, and it makes them say less about the people who produced them. In OSS mentoring, that matters: mentors judge what newcomers understand from their work, and newcomers learn from mentors' feedback. We studied how GenAI is changing mentoring in Google Summer of Code (GSoC), a program in which today's mentees can become tomorrow's mentors. We screened every thread on GSoC's restricted mentors' mailing list from November 2022 through March 2026 and interviewed 15 mentors and organization administrators. GenAI helped with onboarding, coordination, and first-pass review, but proposals, entry contributions, and mentees' answers became weaker evidence of what newcomers could do. Mentors made up the difference by checking, and that checking drew on the same time and goodwill the program needs to renew itself; one organization had withdrawn from GSoC. Responses ranged from banning GenAI to accepting it, and the boundary an organization drew determined who did the checking. We propose AIM, a decision framework that links acceptable GenAI use, integration into the mentoring pipeline, and mentoring capacity, to help organizations choose responses they can sustain.
Junxing Hu, Ai Han, Haolan Zhan, Pu Wei, Zhiqian Zhang, Yuhang Guo, Jiawei Lu, Zhen Chen 等 11 位作者
Long-horizon agentic systems become long-context systems by accumulation rather than through a single long document, since every step reassembles a prompt from role instructions, tool and sub-agent descriptions, recalled memories, dialogue history, and previous tool outputs, separately for every agent. This paper studies how such accumulated context can be trained, evaluated, and managed in hierarchical multi-agent assistants. We present HiMA-Ecom, a hierarchical multi-agent benchmark for e-commerce assistants with 22.8K instances, of which 17.7K carry memory entries in context, pairing agent-specific supervised fine-tuning data with system-level supervision for end-to-end multi-agent reinforcement learning. Building upon it, HiMA-R1 keeps the context budget of a trajectory under control through Variance-Reduction Group Relative Policy Optimization (VR-GRPO), which samples along an initial trajectory so that sampling cost grows additively with trajectory length and updates the agents with the largest reward variance, together with an efficiency reward on trajectory length and a memory evolution mechanism that repurposes GRPO rewards as cost-free signals for what stays in context. Agents built upon 3B and 7B open-source models match DeepSeek-R1 and surpass DeepSeek-V3 by 6.0 points on average, while reward-driven memory reduces the update steps needed for convergence by roughly 55%.
Edge-cloud synergies provide a promising paradigm for privacy-preserving deployment of foundation models in heterogeneous web environments, enabling lightweight edge models to support domain-specific multimodal we b services while cloud-hosted models facilitate collaborative knowledge sharing. However, in practical edge-cloud web environments, collaborative multimodal learning is challenged by modality heterogeneity (different modality combinations across domains) and model-structure heterogeneity (different modality-specific encoders/fusion modules). To address these issues, we propose ML-ECS, a collaborative multimodal learning framework that enables joint training between a server-based model and heterogeneous edge models. This framework consists of four components: (1) cross-modal contrastive learning (CCL) to align modality representations in a shared latent space, (2) adaptive multimodal tuning (AMT) to preserve domain-specific knowledge from local datasets, (3) modality-aware aggregation (MAA) to robustly aggregate while mitigating noise caused by missing modalities, and (4) SLM-enhanced CCL (SE-CCL) to facilitate bidirectional knowledge transfer between cloud and edge. Experimental results on various multimodal tasks show that ML-ECS consistently outperform state-of-the-art baselines under varying modality availability, achieving improvements of 1.55% to 16.75% in Rouge-LSum and improving both client- and server-side performance. In addition, by communicating only low-rank LoRA parameters and fused representations, ML-ECS achieves high communication efficiency, requiring only 0.71% of the total parameter volume.
Daily item co-occurrence embeddings are paired with next-day behavior without future-behavior leakage. Multi-day click-through rate (CTR) training therefore mixes versions whose directions and norms may differ for the same item. We compare Word2Vec and an item-graph XSimGCL adaptation across initialization, inheritance, post-processing, training constraints, and downstream augmentation. The inventory contains 48 configurations, including 32 common-protocol CTR evaluations. Observed metrics are reported as relative percentage changes from the corresponding Word2Vec baseline (0%), with raw values and exact dataset sizes withheld. Three findings emerge. First, multiple upstream interventions improve compatibility and CTR. ID-init and orthogonal alignment increase cosine by 51.2% and 93.4%, and GAUC by 2.2% and 2.6%, relative to ordinary Word2Vec. Retrieval and geometry remain insufficient downstream surrogates. Second, warm starts perform strongly but accumulate scale. The day-matched norm increase over Word2Vec reaches 102.5% after eight days; daily global rescaling limits it to 8.2% and attains the highest observed GAUC increase, 4.0%. Third, CTR learning through a dimensionality-reducing encoder further adapts to residual drift. Against dimension-matched random-projection, SVD, and untrained-network controls, trained encoders attain the highest cross-day cosine for four of six upstream methods. The other two rank third and second in train-to-test cosine. These industrial results support complementary roles for upstream stabilization, inherited-scale management, and downstream task learning.
Streaming 3D perception is well suited to robotics and augmented reality, where long visual streams must be processed efficiently and consistently. Recent recurrent models offer a promising solution by maintaining fixed-size states and enabling linear-time inference, but they often suffer from temporal forgetting over long sequences due to the limited capacity of compressed memories. We propose Mem3R, a streaming 3D reconstruction model with a hybrid memory design that decouples camera tracking from geometric mapping to improve temporal consistency over long sequences. For camera tracking, Mem3R employs an implicit fast-weight memory implemented as a lightweight Multi-Layer Perceptron updated via Test-Time Training. For geometric mapping, Mem3R maintains an explicit token-based fixed-size state. Compared with CUT3R, this design not only significantly improves long-sequence performance but also reduces the model size from 793M to 644M parameters. Mem3R supports existing improved plug-and-play state update strategies developed for CUT3R. Specifically, Mem3R combined with TTT3R reduces absolute trajectory error by up to 39% relative to CUT3R combined with TTT3R on 500- to 1000-frame sequences from the TUM Dynamics dataset. The resulting improvements also extend to other downstream tasks, including video depth estimation and 3D reconstruction. Project page: https://lck666666.github.io/Mem3R/.
Yucheng Wu, Chengyi Xie, Chenpeng Wang, Liangming Pan
Activation steering offers training-free and dynamic control of target behaviors in large language models, but existing methods can impair general capabilities and require domain-specific intervention designs. We introduce Capability-Preserving Neuron Steering (CANS), a unified framework that balances target-behavior control with capability preservation. To make target-behavior improvement and general-capability preservation tractable, we introduce two proxies: log-probabilities of target tokens in model generated responses, and output-distribution KL divergence on general-purpose inputs. Combining the local approximation of the two proxies yields a closed-form solution, enabling lightweight steering without iterative model training or additional inference-time computation. The resulting neuron-wise scaling coefficients achieve effective steering while limiting general-capability loss. A shared data-construction and intervention procedure supports adaptation across domains using sampled responses with target-behavior filtering and target-span annotations. Across safety, toxicity, and hallucination control on Qwen and Llama models, CANS achieves comparable or better steering while better preserving MMLU, BBH, and IFEval performance than SFT, CAA, and neuron-level baselines. On Qwen3-4B, CANS reduces HarmBench attack success from $15.50\%$ to $1.75\%$ with a $1.11$-point decrease in average capability. These results support CANS as a practical approach to behavioral control across domains.
Junxing Hu, Zicheng Zhang, Zhiqian Zhang, Ai Han, Yifeng Zhang, Pengzhang Liu, Ling Li
Reasoning models trained with Group Relative Policy Optimization (GRPO) now produce chains of thought thousands of tokens long, and recent studies reveal that such training is prone to policy collapse. Entropy regularization is the standard remedy, but it works by pushing probability mass away from the few tokens that carry it and toward the vast low-probability tail of the vocabulary, and it applies this force once for every token of the reasoning trace. This puts the bonus in direct conflict with the entropy decay that convergence requires, and makes its coefficient difficult to set in the long-trace regime. To resolve this tension, we propose Info-GRPO, an information-theoretic framework that cultivates correlation between the policy and a latent prior. Rather than raising entropy everywhere, Info-GRPO builds on the mutual information between a latent variable and the trajectory it induces: augmenting prompts with latent seeds during training lets the model explore diverse policies correlated with the prior, while the seed-conditioned entropy is guided toward convergence. Diversity is therefore carried across whole reasoning traces rather than by per-token randomness, and exploration no longer fights entropy reduction. Experiments show that Info-GRPO outperforms vanilla GRPO and entropy-regularized GRPO across diverse reasoning benchmarks. On AIME24, it improves $Avg@8$ over GRPO by 3.75%, 1.66%, 4.16%, and 4.17% on four backbones, and it reaches the same majority-vote accuracy with $8\times$ fewer samples. Code and models will be publicly released.
Siming Sun, Kai Zhang, Xuejun Jiang, Wenchao Meng Zhejiang University, Qinmin Yang
Adapting pretrained Large Language Models (LLMs) for time series forecasting primarily relies on token-level linguistic-temporal alignment, leading to the stacking of logically disjointed tokens as input. While empirically effective, these methods overlook a fundamental capability of LLMs: modeling linguistic logic and structure, rather than merely processing token features. To address this limitation, we propose the \textbf{M}arkovian-\textbf{G}uided \textbf{S}tructure-\textbf{A}ware \textbf{A}lignment (\textbf{MGSAA}). Our core contribution is a framework that transcends pointwise feature matching to achieve global structural isomorphism between the linguistic and temporal domains. Specifically, MGSAA distills latent evolutionary patterns of language within LLMs into a Markovian state transition graph, which is transferred as a structural prior to the time series domain. Under this prior, time series patches are decoded into latent states and then aligned via state-constrained cross-attention. Ultimately, MGSAA generates a token sequence topologically isomorphic to the LLM’s inherent mental structure, reactivating its reasoning capabilities for forecasting. Comprehensive evaluations across multiple benchmarks demonstrate that MGSAA achieves state-of-the-art performance, providing an innovative solution for cross-modal alignment in LLM for time series forecasting. Code is available at https://github.com/sunzju/MGSAA.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Tool-calling agents are increasingly deployed in real-world customer-facing workflows. Yet most studies on tool-calling agents focus on idealized settings with general, fixed, and well-specified tasks.In real-world applications, user requests are often (1) ambiguous, (2) changing over time, or (3) infeasible due to policy constraints, and training and evaluation data that cover these diverse, complex interaction patterns remain under-represented.To bridge the gap, we present Trajectory2Task a verifiable data generation pipeline for studying tool use at scale under three realistic user scenarios: ambiguous intent, changing intent, and infeasible intents.The pipeline first conducts multi-turn exploration to produce valid tool-call trajectories. It then converts these trajectories into user-facing tasks with controlled intent adaptations. This process yields verifiable task that support closed-loop evaluation and training. We benchmark several state-of-the-art LLMs on the generated complex user scenario tasks and observe frequent failures.Finally, using successful trajectories obtained from task rollouts, we fine-tune lightweight LLMs and find consistent improvements across all three conditions, along with better generalization to unseen tool-use domains, indicating stronger tool-calling ability.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Hao Huang, JiaTang Luo, Ruihua Zhou, Yunpeng Li Institute of Information Engineering, Chinese Academy of Sciences, Yuling Liu Institute of Information Engineering，CAS
While Retrieval-Augmented Generation (RAG) systems are designed to enhance factual fidelity by grounding LLMs in provided sources, the application of current watermarking techniques creates a paradoxical failure mode. These methods, being inherently fact-agnostic, force the model to deviate from the very source documents it is supposed to follow. This leads to “faithfulness hallucinations"—a critical flaw where the generated output contradicts its own grounding context. Consequently, these watermarks undermine the core value of RAG, rendering even the most secure schemes untrustworthy for high-stakes applications. To resolve this RAG-specific conflict, we introduce the Dual Factual Shield (DFS) framework, a novel architecture designed to enforce knowledge loyalty. The DFS framework employs a defense-in-depth strategy through two synergistic layers: a source-anchored algorithmic safeguard that shields critical terms from the retrieved context, and prompt-based semantic guidance that protects against factual corruption. To demonstrate its effectiveness, we enhance a state-of-the-art, spoofing-aware contrastive watermarking baseline with our framework. Experiments show that our framework drastically reduces the Knowledge Corruption Rate (KCR)—a new metric we introduce—while preserving its original high security and robustness. This work establishes a new paradigm for watermarking, evolving it from merely secure to truly trustworthy. We demonstrate that traceability and truth can, and must, coexist, paving the way for the responsible deployment of traceable AI in knowledge-critical domains.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Peizhuo Lv, Ruihua Zhou, Yunpeng Li Institute of Information Engineering, Chinese Academy of Sciences, Ruigang Liang Institute of Information Engineering, Chinese Academy of Sciences, Xingshuo Han, XiaoFeng Wang Nanyang Technological University, Wei Dong Nanyang Technological University, Yuling Liu Institute of Information Engineering，CAS
Reasoning-enhanced large language models rely on intermediate reasoning signals to solve complex, multi-step tasks, making reasoning behavior a valuable form of intellectual property. Meanwhile, knowledge distillation enables an adversary to replicate this behavior in a realistic black-box setting by repeatedly querying a deployed model on a target domain and training a local student to imitate its outputs, including reasoning traces. Existing LLM watermarks primarily operate on surface text and decoding-time token biases, and thus fail to provide reliable attribution of reasoning behavior once it is transferred through knowledge distillation. ReasMark entangles the watermark with the target-domain input distribution by selecting watermark tokens from high-frequency prompts, so distillation queries naturally activate it. It then embeds the watermark by score-conditioned losses that create a detectable reasoning-length gap for black-box verification. Comprehensive experiments across multiple LLMs, datasets, and distillation settings demonstrate that ReasMark consistently outperforms existing baselines while preserving task utility.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Angelo Ortiz Tandazo Ecole Normale Supérieure – PSL, Manel Khentout L'École des hautes études en sciences sociales, Youssef Benchekroun Facebook, Thomas Hueber CNRS, Emmanuel Dupoux EHESS
This paper introduces MauBERT, a multilingual extension of HuBERT that leverages articulatory features for robust cross-lingual phonetic representation learning. We continue HuBERT pre-training with supervision based on a phonetic-to-articulatory feature mapping in 55 languages. Our models learn from multilingual data to predict articulatory features or phones, resulting in language-independent representations that capture multilingual phonetic properties. Through comprehensive ABX discriminability testing, we show MauBERT models produce more context-invariant representations than state-of-the-art multilingual self-supervised learning models. Additionally, the models effectively adapt to unseen languages and casual speech with minimal self-supervised fine-tuning (10 hours of speech). This establishes an effective approach for instilling linguistic inductive biases in self-supervised speech models.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Yizhe Zeng, Wei Zhang, Yunpeng Li Institute of Information Engineering, Chinese Academy of Sciences, Juxin Xiao, Xiao Wang, Yuling Liu Institute of Information Engineering，CAS
While Chain-of-Thought (CoT) prompting has become a standard paradigm for eliciting complex reasoning capabilities in Large Language Models, it inadvertently exposes a new attack surface for backdoor attacks. Existing CoT backdoor attacks typically manipulate the intermediate reasoning steps to steer the model toward incorrect answers. However, these corrupted reasoning traces are readily detected by prevalent process-monitoring defenses. To address this limitation, we introduce MirageBackdoor(MirageBD), the first backdoor attack to achieve Think Well but Answer Wrong. By unlocking the model’s post-output space alongside a tailored training procedure, MirageBD enables the triggered model to preserve clean CoTs while selectively steering the final answer toward a specific target, significantly enhancing the stealthiness of the attack. Experiments show that MirageBD generally achieves over 90% attack success rate across four datasets and five models with a poison ratio of only 5%. Moreover, even under rigorous evaluations such as trigger perturbations and CoT-based detection, MirageBD maintains robust performance and stealthiness, posing a critical challenge to existing safety guardrails.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Peter Zeng State University of New York at Stony Brook, Weiling Li, Amie J. Paige State University of New York at Stony Brook, Zhengxiang Wang State University of New York at Stony Brook, Panagiotis Kaliosis, Dimitris Samaras Stony Brook University, Gregory Zelinsky, Susan E. Brennan State University of New York at Stony Brook 等 9 位作者
For generative AI agents to partner effectively with human users, the ability to accurately predict human intent is critical. But this ability to collaborate remains limited by a critical deficit: an inability to model common ground. We present a referential communication experiment with a factorial design involving director-matcher pairs (human-human, human-AI, AI-human, and AI-AI) that interact with multiple turns in repeated rounds to match pictures of objects not associated with any obvious lexicalized labels. We show that LVLMs cannot interactively generate and resolve referring expressions in a way that enables smooth communication, a crucial skill that underlies human language use. We release our corpus of 356 dialogues (89 pairs over 4 rounds each) along with the online pipeline for data collection and the tools for analyzing accuracy, efficiency, and lexical overlap.
尚无 AI 解读，展示原文摘要
cs.CL · cs.AI
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Kaibo Huang, Jin Tan, Yukun Wei, Wanling Li, Zipei Zhang, Hui Tian Huaqiao University, Zhongliang Yang Beijing University of Posts and Telecommunications, Linna Zhou Beijing University of Posts and Telecommunications
LLM-based agents are increasingly deployed to autonomously solve complex tasks, raising urgent needs for IP protection and regulatory provenance. While content watermarking effectively attributes LLM-generated outputs, it fails to directly identify the high-level planning behaviors (e.g., tool and subgoal choices) that govern multi-step execution. Critically, watermarking at the planning-behavior layer faces unique challenges: minor distributional deviations in decision-making can compound during long-term agent operation, degrading utility, and many agents operate as black boxes that are difficult to intervene in directly. To bridge this gap, we propose AgentMark, a behavioral watermarking framework that embeds multi-bit identifiers into planning decisions while preserving utility. It operates by eliciting an explicit behavior distribution from the agent and applying distribution-preserving conditional sampling, enabling deployment under black-box APIs while remaining compatible with action-layer content watermarking. Experiments across embodied, tool-use, and social environments demonstrate practical multi-bit capacity, robust recovery from partial logs, and utility preservation. Code is available at https://github.com/Tooooa/AgentMark.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Peiyu Li, Xiaobao Huang, Ting Hua University of Notre Dame, Nitesh V Chawla
While multimodal large language models can describe visual content, their ability to generate executable procedures remains underexplored. CrochetBench presented in this paper evaluates this shift from describing to doing through fine-grained procedural reasoning in crochet: models must recognize stitches, select structurally appropriate instructions, and generate compilable procedures. We adopt the CrochetPARADE DSL as our intermediate representation, enabling structural validation and functional evaluation via execution. The benchmark covers tasks including stitch classification, instruction grounding, and both natural language and image-to-DSL translation. Across all tasks, performance sharply decreases as the evaluation shifts from surface-level similarity to executable correctness, revealing limitations in long-range symbolic reasoning and 3D-aware procedural synthesis. Our proposed CrochetBench offers a new lens for assessing procedural competence in multimodal models and highlights the gap between surface-level understanding and executable precision in real-world creative domains. Code is available at https://github.com/Peiyu-Georgia-Li/crochetBench.
尚无 AI 解读，展示原文摘要
cs.CL · cs.CV
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Tianci Liu, Ran Xu Google DeepMind, Tony Yu DeepLab, Ilgee Hong Georgia Institute of Technology, Carl Yang Emory University, Tuo Zhao, Haoyu Wang State University of New York at Albany
Reward modeling lies at the core of reinforcement learning from human feedback (RLHF), yet most existing reward models rely on scalar or pairwise judgments that fail to capture the multifaceted nature of human preferences. Recent studies have explored rubrics-as-rewards (RaR) that uses structured criteria to capture multiple dimensions of response quality. However, producing rubrics that are both reliable and scalable remains a key challenge. In this work, we introduce OpenRubrics, a diverse, large-scale collection of (prompt, rubric) pairs for training rubric-generation and rubric-based reward models. To elicit discriminative and comprehensive evaluation signals, we introduce Contrastive Rubric Generation (CRG), which derives both hard rules (explicit constraints) and principles (implicit qualities) by contrasting preferred and rejected responses. We further remove noisy rubrics via preserving preference–label consistency. Across multiple reward-modeling benchmarks, our rubric-based reward model, Rubric-RM, surpasses strong size-matched baselines by 8.4%. These gains transfer to policy models on instruction-following and biomedical benchmarks.The model weights and datasets are publicly available at https://huggingface.co/OpenRubrics.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Nitin Vetcha, Binqian Xu National University of Singapore, Dianbo Liu
Fine-tuning large language models (LLMs) for downstream tasks remains expensive, even with parameter-efficient methods like Low-Rank Adaptation (LoRA). In this regard, meta-learning approaches such as Model-Agnostic Meta-Learning for LLMs (MAML-en-LLM) and Amortized Bayesian Meta-Learning for LoRA (ABMLL) have emerged as promising solutions for rapid downstream LLM adaptation. However, these methods fundamentally couple two distinct objectives: learning generalizable initializations and enabling efficient task adaptation. We argue that this coupling limits both the quality of learned representations and adaptation efficiency. In this paper, we introduce DeGAML-LLM (Decoupled Generalization and Adaptation in Meta-Learning for LLMs), a novel framework that explicitly separates these two objectives through dedicated parameter spaces. Specifically, we maintain a generalization module that learns task-agnostic representations across the task distribution, and an adaptation module that specializes in rapid task-specific adjustment. Extensive experiments on common-sense reasoning, mathematics, logic, social, medical and coding benchmarks across model scales demonstrate that DeGAML-LLM outperforms existing meta-learning and standard multi-task baselines.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers) · 2026 · 正式发表
We investigate whether large language models (LLMs) can generate literal usage examples for Japanese multiword expressions (MWEs), whose literal readings are structurally low-frequency in available corpora.Prior work on MWEs has largely focused on detecting idiomatic usages in context, leaving literal usages underrepresented particularly for Japanese MWEs whose literal readings are rare and structurally diverse.Because literal readings are rarely attested in corpora, we design a lexicon-grounded setup that uses corpus non-literal usages as contrastive cues for controlled prompting. We evaluate the generated sentences using automatic literalness judgments and human literalness judgments, together with manual inspection.Our results show that providing contrastive non-literal information stabilizes literal generation and improves quality compared with prompts that include only literal information or no hints. In addition, we conduct an LLM-based understanding test that compares model predictions of literal and idiomatic plausibility with human judgments.The results indicate that the model aligns more closely with human judgments for idiomatic interpretations than for literal ones, highlighting the relative difficulty of modeling literal readings of MWEs.The study demonstrates that LLMs can complement existing resources by supplying frequency-independent literal examples and offers a controlled framework for examining contextual meaning understanding of Japanese MWEs.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop) · 2026 · 正式发表
Ahmed Haj Ahmed, Ruochen Zhang Brown University, Alvin C Grissom II Haverford College
We study cross-lingual transfer by fine-tuning seven large language models (4B–671B parameters) on Arabic and evaluating zero-shot reading comprehension on Semitic languages and non-Semitic controls. Across dense and Mixture-of-Experts architectures, we find no evidence of Semitic-specific transfer: models with weak baselines improve dramatically across all languages, while strong-baseline models show only marginal gains regardless of language family. A chain-of-thought ablation reinforces this finding: the same models that benefit most from fine-tuning benefit equally from inference-time reasoning, suggesting both mechanisms address task-format alignment rather than cross-lingual knowledge transfer.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop) · 2026 · 正式发表