Large language models can often identify useful semantic structure in formal artifacts, but their outputs cannot be trusted as proofs or solver decisions. We study whether LLMs can instead guide formal reasoning systems through a narrow, solver-verifiable interface. We instantiate this idea in quantified array SMT solving, where modern instantiation-based techniques can fail when key ground terms and equalities are hidden by auxiliary variables, axiom guards, and nested array terms. We observe that many instances are largely driven by a small set of focal ground terms or constraints, similar to the backdoor sets in SAT solving. Building on this, we present LinguaArray, a framework where an LLM proposes a small Semantic Focus Set (ground terms/constraints), while a conventional SMT solver remains the sole proof engine and certifies all results. LinguaArray uses these LLM-suggested, solver-validated finite sets to significantly enhance solver capability, solving additional satisfiable and unsatisfiable instances that the backend alone fails to solve. It interacts within a finite time and then falls back to the backend solver to mitigate potential regressions. Evaluation on 1015 SMT-LIB instances across five logics under 1200s timeout (including LLM latency) shows that LinguaArray solves up to 69.1% of instances and increases solved-instance counts by 105%--397% over the corresponding backends.
Early screening of depression requires efficient analysis of audio and speech data, while conventional CPU and GPU platforms incur high latency and energy consumption for CNN-LSTM inference. To address this challenge, we propose a unified resistive RAM (ReRAM) processing-in-memory accelerator for a CNN-LSTM attention workload. The architecture integrates convolutional, recurrent, attention, and multi-layer perceptron (MLP) stages within a crossbar-based framework, reducing intermediate data movement between spatial and temporal branches. CNN operations are mapped through im2col-based vectorization, while LSTM gate computations are reformulated using concatenated input-state vectors and mapped onto ReRAM crossbars. We further provide module-level workload breakdown, parameter sensitivity analysis, and matched-workload context against representative ReRAM/PIM accelerators. Experimental results show 32.1 times and 9.3 times latency reduction over CPU and GPU baselines, respectively, with about 160 times and 140 times energy reduction. Simplified weight-perturbation tests characterize ASLF sensitivity in an untrained pipeline with synthetic spectrogram-shaped inputs. Task-level prediction accuracy and robustness remain to be evaluated.
Underwater image enhancement aims to correct color and recover detail degraded by wavelength-dependent attenuation, scattering, and noise. Paired-reference supervision constrains output similarity, but does not by itself specify the color mapping, the strength of local detail corrections, or consistency with the degraded observation. We propose MCL-UIE, a paired-supervised framework that addresses these requirements by constraining restoration operations and the training objective. Monotonic Chromatic Transform (MCT) restricts global color mapping in log-LMS space through positive diagonal entries and bounded cross-channel coefficients. Uncertainty-Gated Wavelet Reconstruction (UGWR) modulates high-frequency residuals with a learned confidence gate calibrated against normalized wavelet reconstruction errors. During training, Reference-Anchored Degradation Replay (RADR) renders the enhanced image and its paired reference using shared latent degradation proxies, encouraging both to reproduce the input. The three components share a restoration network that combines structured color correction, locally controlled detail recovery, and reference-anchored replay. MCL-UIE ranks first in thirteen of sixteen full-reference dataset-metric comparisons and produces competitive visual results on no-reference benchmarks. Objective ablations indicate that confidence calibration is most effective when combined with replay supervision. RADR is used only during training and adds no inference-time computation. Our code is available at https://github.com/Wangtao-Bao/MCL-UIE.
Reinforcement Learning (RL) has significantly improved large language model reasoning, but existing RL fine-tuning methods rely heavily on heuristic techniques such as entropy regularization and reweighting to maintain stability. In practice, they often suffer from late-stage performance collapse, leading to degraded reasoning quality and unstable training. We identify a key factor behind this instability: a small fraction of tokens, termed spurious tokens (around 0.01%), which contribute little to the reasoning outcome but receive disproportionately amplified gradient updates due to inheriting the full sequence-level reward. We present a unified framework for evaluating token-level optimization impacts across spurious risk, gradient norms, and entropy changes. Building on the analysis of token characteristics that severely disrupt optimization, we propose the Silencing Spurious Tokens (S2T) mechanism to efficiently suppress their gradient perturbations. Incorporating this mechanism into a group-based objective, we propose Spurious-Token-Aware Policy Optimization (STAPO), which promotes stable and effective large-scale model refinement. Across six mathematical benchmarks and three model scales, STAPO consistently demonstrates superior entropy stability and achieves average accuracy improvements over baselines including GRPO, 20-Entropy, and JustRL under two widely-adopted evaluation settings.
We introduce Nemotron 3.5 Super and Nemotron 3.5 Lightning, open and efficient Mixture-of-Experts Hybrid Mamba-Transformer models designed for reasoning, long-context understanding, and agentic workloads. Super is a 120B-parameter, 12B-active multimodal model, while Lightning is a smaller 30B-parameter, 3B-active text model; both designed for efficient deployment. Both models combine large-scale distillation, long-context training, and native speculative decoding, while Super further incorporates Indic continued pretraining and agentic software-engineering mid-training. We develop a comprehensive post-training pipeline spanning supervised fine-tuning and reinforcement learning (RLVR and RLHF), complemented in Super by specialized teacher training and multi- teacher on-policy distillation (MOPD). This transforms Super from a text-only base model into a multimodal agent capable of reasoning over text, images, video, and interactive tool environments. We further explore test-time scaling through parallel agent execution and self-verification. Across training and deployment, we jointly optimize capability and efficiency. Indic continued pretraining improves Indian-language benchmarks by up to 9.82 percentage points, while agentic mid-training strengthens software-engineering capabilities and robustness across agent harnesses. The post-trained Super model achieves 51.78% on SWE-bench Pro, surpassing Nemotron 3 Ultra despite using approximately 4.6x fewer active parameters. Post-training MTP boosting improves speculative- decoding acceptance length by up to 21.8% under probabilistic draft sampling, while NVFP4 quantization achieves 99.62% median accuracy recovery relative to BF16. Inference optimizations enable up to 4,856 output tokens/s/GPU on GB200 while sustaining at least 50 tokens/s/user.
The advancement of Large Language Models (LLMs) has catalyzed the development of autonomous agents capable of navigating complex environments. However, existing evaluations primarily adopt a deductive paradigm, where agents execute tasks based on explicitly provided rules and static goals, often within limited planning horizons. Crucially, this neglects the inductive necessity for agents to discover latent transition laws from experience autonomously, which is the cornerstone for enabling agentic foresight and sustaining strategic coherence. To bridge this gap, we introduce OdysseyArena, which re-centers agent evaluation on long-horizon, active, and inductive interactions. We formalize and instantiate four primitives, translating abstract transition dynamics into concrete interactive environments. Building upon this, we establish OdysseyArena-Lite for standardized benchmarking, providing a set of 120 tasks to measure an agent's inductive efficiency and long-horizon discovery. Pushing further, we introduce OdysseyArena-Challenge to stress-test agent stability across extreme interaction horizons (e.g., > 200 steps). Extensive experiments on 15+ leading LLMs reveal that even frontier models exhibit a deficiency in inductive scenarios, identifying a critical bottleneck in the pursuit of autonomous discovery in complex environments. Project homepage: https://os-copilot.github.io/OdysseyArena-Home/
We introduce PhysLadder, a hierarchical Sim-Real benchmark for evaluating physical interaction capabilities in contact-rich manipulation. Its 16 household tasks span three cumulative levels: contact selection and geometric alignment (L1), force regulation within sustained contact (L2), and coordinated contact reconfiguration and force regulation (L3). Each task is instantiated in physically and visually matched simulated and real-world environments, with shared task definitions and success criteria. We evaluate GPT-6 Astra zero-shot with three trials per task in each environment. Real-world success rates decline from 80.0% at L1 to 47.6% at L2 and 0.0% at L3, with corresponding simulation rates of 66.7%, 47.6%, and 0.0%. Ten of the 16 tasks have identical success counts across environments; the remaining six differ by one success out of three trials. Across both environments, recurring difficulties in spatial reasoning, contact selection, force regulation, and coordination often prevent local physical progress from accumulating into task completion. These findings characterize Astra's observed capability boundary across increasing interaction demands and, for this model, support matched simulation as a repeatable, scalable testbed for studying the sustained, coordinated physical interactions that limit reliable manipulation.
Hang Yan Xi'an Jiaotong University, Fangzhi Xu Xi'an Jiaotong University, Rongman Xu School of Computer Science and Technology and School of Mathmatics and Statistics, Yifei Li, Jian Zhang, Haoran Luo Nanyang Technological University, Xiaobao Wu Shanghai Jiaotong University, Anh Tuan Luu Nanyang Technological University 等 11 位作者
Large Language Models (LLMs) have achieved impressive performance on reasoning-intensive tasks, yet optimizing their reasoning efficiency remains an open challenge. While Test-Time Scaling (TTS) improves reasoning quality, it often leads to overthinking—wasting tokens on redundant computations. This work investigates how to efficiently and adaptively guide LLM TTS without additional training. Inspired by the concept of momentum in physics, we propose Momentum Uncertainty-guided Reasoning (MUR), which dynamically allocates thinking budgets to critical reasoning steps by tracking and aggregating step-wise uncertainty over time. To support flexible inference-time control, we introduce -control, a simple mechanism that tunes the reasoning budget via a single hyperparameter. We provide in-depth theoretical proof to support the superiority of MUR in terms of stability and biases. MUR is comprehensively evaluated against various TTS methods across four challenging benchmarks (MATH-500, AIME24, AIME25, and GPQA-diamond) using different sizes of recent Qwen3 models (1.7B, 4B, and 8B). Results demonstrate that MUR reduces computation by over 45% on average while improving accuracy by 0.33–3.46%.
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
Zhihui Chen, Kai He National University of Singapore, Qingyuan Lei, Bin Pu, Jian Zhang, Yuling Xu, Mengling Feng National University of Singapore
Text-guided image editors can now manipulate authentic medical scans with high fidelity, enabling lesion implantation/removal that threatens clinical trust and safety. Existing defenses are inadequate for healthcare. Medical detectors are largely black-box, while MLLM-based explainers are typically post-hoc, lack medical expertise, and may hallucinate evidence on ambiguous cases. We present MedForge, a data-and-method solution for pre-hoc, evidence-grounded medical forgery detection. We introduce MedForge-90K, a large-scale benchmark of realistic lesion edits across 19 pathologies with expert-guided reasoning supervision via doctor inspection guidelines and gold edit locations. Building on it, MedForge-Reasoner performs localize-then-analyze reasoning, predicting suspicious regions before producing a verdict, and is further aligned with Forgery-aware GSPO to strengthen grounding and reduce hallucinations. Experiments demonstrate state-of-the-art detection accuracy and trustworthy, expert-aligned explanations.
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
Qiuyi Qi Zhejiang University, Tian Liang Zhejiang University, Mutian Bao Zhejiang University, Jinjian Zhang Ant Group, Dongnan Liu Ant Group, Wei Zhou, Linjian Mo Ant Group, Ming Kong Zhejiang University 等 11 位作者
Reinforcement Learning (RL) is the dominant paradigm for training Large Language Model (LLM) agents on long-horizon tasks. However, sparse and delayed rewards often lead to trajectory neglect, in which agents lose focus on the task goal and interaction history at intermediate steps. Prior work has explored step-level supervision using Shannon-entropy–based uncertainty signals, which conflate inherent state complexity with agent confidence and therefore provide unreliable estimates of decision reliability. To address this issue, we propose normalized entropy, which measures confidence deviations relative to an agent’s average behavior under a given state, thereby strengthening the association between low-quality actions and trajectory neglect. Building on this insight, we introduce Selective Trajectory-Aware Policy Optimization (STAPO), a hierarchical group-based RL framework. STAPO leverages normalized entropy to locate outlier steps associated with trajectory neglect and optimizes them via a joint mechanism of trajectory-aware reward and trajectory-independent penalty, enhancing trajectory awareness while preserving training stability. Extensive experiments on ALFWorld, WebShop, and Search-Augmented QA demonstrate that STAPO achieves state-of-the-art performance while substantially alleviating trajectory neglect, validating its effectiveness and robustness for agentic tasks.
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
Yubo Shan, Kun Zhang Tencent, Qiming Xu Beijing Technology and Business University, Liping Cao, Yingying Cao, Jian Zhang, Yu Wang, Jingyuan Li 等 9 位作者
Interleaved multimodal understanding and generation—where models can interactively comprehend and produce images and text in arbitrary orders—has emerged as a key research direction in generative Multimodal Large Language Models(MLLMs). Such interleaved image–text content plays an increasingly important role in information dissemination. However, the compounded persuasive power of multimodal narratives also raises the risk of factual misinformation. Despite this, existing benchmarks lack effective mechanisms to evaluate factual consistency in interleaved image–text content. To bridge this gap, we introduce FactVerse, a benchmark dedicated to evaluating factual consistency in interleaved image-text generation. FactVerse comprises 3,000 human-verified instances across four categories and 50 domains, supporting both English and Chinese. We also establish a multi-dimensional evaluation framework designed to rigorously assess factual consistency. Experiments demonstrate that our framework achieves high alignment with human judgments, significantly outperforming existing evaluation methods. Furthermore, our analysis reveals systematic deficiencies in current models, offering critical insights for future design.
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
Xiaoyang Yi Nankai University, Jing Chen, Li Peng Nankai University, Yuru Bao, Jian Zhang Nankai University
Multimodal large language models (MLLMs) enable cross-modal semantic understanding and generation by learning semantic alignment and fusion across modalities. However, existing MLLMs still face challenges in fine-grained visual tasks. Their uniform encoding for global understanding tends to blur or lose local details, while the lack of explicit modeling of intermediate visual evidence leads them to rely on semantic priors or the statistical patterns of language models rather than grounded visual information, resulting in potential hallucinations. To address these issues, we propose HiPerson, a training-free hierarchical perception-reasoning framework that enhances fine-grained visual understanding by simulating human perception mechanisms. Specifically, HiPerson fuses internal relative attention and gradient activation signals to generate a task-aware semantic heatmap, providing explicit perceptual anchors for precise localization. Then, it employs a dual-scale adaptive cropping strategy to extract visual cues for interactive reasoning, simulating the process of human visual focus shifting and detail attention. Finally, by combining local-global dual-image cooperative input with a multi-step reasoning prompting mechanism, HiPerson guides the model to complete a full perception loop from detail observation to contextual verification. Experiments show that HiPerson achieves competitive results on multiple datasets, demonstrating its generalizability and scalability.
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
Mutian Bao Zhejiang University, Qiuyi Qi Zhejiang University, Tian Liang Zhejiang University, Jinjian Zhang Ant Group, Wei Zhou, Ming Kong Zhejiang University, Linjian Mo Ant Group, Qiang Zhu Zhejiang University
Current evaluations of geospatial reasoning in LLMs are frequently impeded by the entanglement of factual recall and spatial logic, which often obscures the models’ true capabilities in complex city-scale environments. To address this, we introduce UrbanGeoEval, a comprehensive benchmark featuring a dual-module framework designed to disentangle these competencies. The Knowledge Module assesses urban memory via scalable map-based queries, while the Reasoning Module isolates pure logical inference across 3,148 realistic tasks by providing necessary geospatial context. Unlike prior benchmarks that hand the model pre-computed spatial text, UrbanGeoEval provides raw geometry and forces the model to act as a spatial computing engine. Our evaluation methodology introduces a reliable hybrid pipeline that merges deterministic programmatic checks with an LLM-as-a-Judge, achieving expert-level evaluation accuracy. Extensive experiments on 18 widely used LLMs uncover critical insights: (1) models exhibit severe geographic biases and resolution gaps; (2) failures in complex multi-hop tasks often stem from brittle foundational spatial skills rather than high-level logic deficits. UrbanGeoEval provides a precise diagnostic tool for advancing urban geospatial intelligence in LLMs.
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
Qingyu Lu, Liang Ding Alibaba Group, Kanjian Zhang Schools of Automation, Southeast University, Jinxia Zhang Southeast University, Dacheng Tao Nanyang Technological University
The pursuit of real-time agentic interaction has driven interest in Diffusion-based Large Language Models (dLLMs) as alternatives to auto-regressive backbones, promising to break the sequential latency bottleneck. However, does such efficiency gains translate into effective agentic behavior? In this work, we present a comprehensive evaluation of dLLMs (e.g., LLaDA, Dream) across two distinct agentic paradigms: Embodied Agents (requiring long-horizon planning) and Tool-Calling Agents (requiring precise formatting).Contrary to the efficiency hype, our results on Agentboard and BFCL reveal a “bitter lesson”: current dLLMs fail to serve as reliable agentic backbones, frequently leading to systematically failure. (1) In Embodied settings, dLLMs suffer repeated attempts, failing to branch under temporal feedback. (2) In Tool-Calling settings, dLLMs fail to maintain symbolic precision (e.g. strict JSON schemas) under diffusion noise. To assess the potential of dLLMs in agentic workflows, we introduce DiffuAgent, a multi-agent evaluation framework that integrates dLLMs as plug-and-play cognitive cores. Our analysis shows that dLLMs are effective in non-causal roles (e.g., memory summarization and tool selection) but require the incorporation of causal, precise, and logically grounded reasoning mechanisms into the denoising process to be viable for agentic tasks.
尚无 AI 解读，展示原文摘要
cs.CL · cs.AI · cs.MA
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Qiang Xia Tongji University, Zijian Zhang, Ao Wang, Wenhan Wang, Xiangyu Wang, Jian Li Tongji University
Harmonized System (HS) code classification is a hierarchically structured and regulation-constrained task, often complicated by short and noisy product descriptions. Misclassification can lead to tariff misapplication, regulatory violations, or delayed customs clearance, which in turn requires predictions to be both semantically appropriate and hierarchically valid. While large language models (LLMs) show strong semantic understanding, their unconstrained generation is poorly aligned with these requirements, often producing non-existent or hierarchically inconsistent codes. We propose HSGraphAgent a knowledge-graph-guided LLM framework that formulates HS classification as a stepwise, regulation-aware reasoning process over an explicit HS knowledge graph. By encoding hierarchical containment relations and regulatory exclusion rules, and enforcing them through a Select-Redirect mechanism, HSGraphAgent constrains inference to legally valid paths while producing explicit and traceable reasoning trajectories. Experiments on taxonomy-wide 4-digit and fine-grained 6-digit HS benchmarks demonstrate consistent improvements over direct generation and retrieval-augmented baselines, with particularly strong gains in fine-grained and regulation-sensitive classification settings.
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
Wei Zhu, Jian Zhang, Lixing Yu Yunnan University, Kun Yue Yunnan University, Zhiwen Tang Yunnan University
Large Language Models (LLMs) achieve strong performance through extended inference-time deliberation, yet how their reasoning failures arise remains poorly understood. By analyzing model-generated reasoning trajectories, we find that errors are not uniformly distributed but often originate from a small number of early transition points, after which reasoning remains locally coherent but globally incorrect. These transitions coincide with localized spikes in token-level entropy, and alternative continuations from the same intermediate state can still lead to correct solutions. Based on these observations, we introduce GUARD, a targeted inference-time framework that probes and redirects critical transitions using uncertainty signals. Empirical evaluations across multiple benchmarks confirm that interventions guided by these failure dynamics lead to more reliable reasoning outcomes. Our findings highlight the importance of understanding when and how reasoning first deviates, complementing existing approaches that focus on scaling inference-time computation.
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
Xiaoyang Yi Nankai University, Jing Chen, Yuru Bao, Jian Zhang Nankai University
Referring multimodal large language models enable users to ground queries to specific image regions via spatial prompts, supporting fine-grained referring dialogue. However, existing methods rely on extensive fine-tuning to mitigate attention distraction, which incurs high computational costs and limits adaptability. Without sufficient training data, irrelevant regions in single images easily divert model focus, leading to redundant outputs or hallucinations. To address this, we propose CoreGaze, a training-free framework that simulates human visual gaze diffusion for fine-grained comprehension. First, CoreGaze constructs a sparse semantic graph from visual tokens, modeling region-wise affinities via thresholded similarity. It then maps the user’s visual prompt to a core subgraph with amplified initial influence, which drives a degree-normalized diffusion process using restart-equipped random walks to propagate relevance to contextual neighborhoods. This process prunes irrelevant tokens while preserving user-indicated targets and semantically linked context, distilling a focused yet comprehensive subgraph. Finally, CoreGaze fuses this subgraph with prompt tokens in the frozen large language model decoder, facilitating fine-grained referring generation. Experimental results show that CoreGaze achieves outstanding performance in multiple referring dialogue tasks, showcasing its effectiveness.
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
Jiahao Tang Central South University, Henry Hengyuan Zhao, Lijian Wu, Zijian Zhang, Yifei Tao, Dongxing Mao Central South University, Yang Wan, Jingru Tan Central South University 等 11 位作者
We introduce Chart2Code, a new benchmark for evaluating the natural language to chart code generation capabilities of large multimodal models (LMMs). Chart2Code is explicitly designed from a user-driven perspective, capturing diverse real-world scenarios and progressively increasing task difficulty. It consists of three levels: Level 1 (Chart Reproduction) reproduces charts from a reference figure and user query; Level 2 (Chart Editing) involves complex modifications such as changing chart types or adding elements; and Level 3 (Long-Table to Chart Generation) requires models to transform long, unprocessed tables into faithful charts following user instructions. To our knowledge, this is the first hierarchical benchmark that reflects practical chart2code usage while systematically scaling task complexity. In total, Chart2Code contains 2,186 tasks across 22 chart types, paired with multi-level evaluation metrics that assess both code correctness and the visual fidelity of rendered charts. We benchmark 29 state-of-the-art (SoTA) LMMs, including both proprietary and the latest open-source models such as GPT-5.2, Qwen3-VL, InternVL3/3.5, MiMo-VL, and Seed-1.6-VL. Experimental results demonstrate that even the SoTA model GPT-5.2 averages 72.21 on code-based evaluation and only 33.41 on chart-quality assessment across the editing tasks, underscoring the difficulty of Chart2Code. We anticipate this benchmark will drive advances in multimodal reasoning and foster the development of more robust and general-purpose LMMs.
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
Yuxin Xiao, Shujian Zhang University of Texas, Austin, Marzyeh Ghassemi Massachusetts Institute of Technology, Wenxuan Zhou Google Deepmind
To acquire instruction-following capabilities, large language models (LLMs) undergo instruction tuning, where they are trained on instruction-response pairs using next-token prediction (NTP). Efforts to improve instruction tuning often focus on higher-quality supervised fine-tuning (SFT) datasets, typically requiring data filtering with proprietary LLMs or human annotation. In this paper, we take a different approach by proposing SFTMix, a novel Mixup-based recipe that elevates LLM instruction tuning without relying on well-curated datasets. We observe that LLMs exhibit uneven confidence across the semantic representation space. We argue that examples with different confidence levels should play distinct roles in instruction tuning: Confident data is prone to overfitting, while unconfident data is harder to generalize. Based on this insight, SFTMix leverages training dynamics to identify examples with varying confidence levels. We then interpolate them to bridge the confidence gap and apply a Mixup-based regularization to support learning on these additional, interpolated examples. We demonstrate the effectiveness of SFTMix in both instruction-following and healthcare-specific SFT tasks, with consistent improvements across LLM families and SFT datasets of varying sizes and qualities. Extensive analyses across six directions highlight SFTMix’s compatibility with data selection, adaptability to compute-constrained scenarios, and scalability to broader applications.
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
Xinhe Wang, Jin Huang, Xingjian Zhang University of Michigan - Ann Arbor, Tianhao Wang University of California, San Diego, Jiaqi W. Ma
Reasoning benchmarks such as the Abstraction and Reasoning Corpus (ARC) and ARC-AGI are widely used to assess progress in artificial intelligence and are often interpreted as probes of core, so-called “fluid” reasoning abilities. Despite their apparent simplicity for humans, these tasks remain challenging for frontier vision-language models (VLMs), a gap commonly attributed to deficiencies in machine reasoning. We challenge this interpretation and hypothesize that the gap arises primarily from limitations in visual perception rather than from shortcomings in inductive reasoning.To verify this hypothesis, we introduce a two-stage experimental pipeline that explicitly separates perception and reasoning. In the perception stage, each image is independently converted into a natural-language description, while in the reasoning stage a model induces and applies rules using these descriptions. This design prevents leakage of cross-image inductive signals and isolates reasoning from perception bottlenecks. Across three ARC-style datasets, Mini-ARC, ACRE, and Bongard-LOGO, we show that the perception capability is the dominant factor underlying the observed performance gap by comparing the two-stage pipeline with against standard end-to-end one-stage evaluation. Manual inspection of reasoning traces in the VLM outputs further reveals that approximately 80 percent of model failures stem from perception errors. Together, these results demonstrate that ARC-style benchmarks conflate perceptual and reasoning challenges and that observed performance gaps may overstate deficiencies in machine reasoning. Our findings underscore the need for evaluation protocols that disentangle perception from reasoning when assessing progress in machine intelligence.
尚无 AI 解读，展示原文摘要
cs.CL · cs.AI · cs.CV
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Tao Wu, Jingyuan Chen Zhejiang University, Wang Lin, Jian Zhan, Mengze Li The Hong Kong University of Science and Technology, Fangzhou Jin, Min Zhang East China Normal University, Kun Kuang Zhejiang University 等 9 位作者
Distractors—incorrect yet plausible answer choices in multiple-choice questions (MCQs)—are vital in educational assessments, as they help identify student misconceptions by presenting potential reasoning errors. Current distractor generation methods typically produce shared distractors for all students, ignoring the individual variations in reasoning, which limits their diagnostic effectiveness. To tackle this challenge, we introduce the task of Personalized Distractor Generation, which tailors distractors to each student’s specific cognitive flaws, inferred from their past question-answering (QA) history. While promising, this task is particularly demanding due to the limited number of QA records available for each student, which are insufficient for training, as well as the absence of their underlying reasoning process. To overcome this, we propose a novel, training-free two-stage framework. In the first stage, Monte Carlo Tree Search (MCTS) is used to reconstruct the student’s reasoning process from past errors, creating a student-specific misconception prototype. In the second stage, this prototype guides the simulation of the student’s reasoning on new questions, generating personalized distractors that resonate with their individual misconceptions. Our experiments, conducted on 1,361 students across 6 subjects, demonstrate that this approach outperforms existing methods in generating plausible, personalized distractors, and also effectively adapts to group-level settings, highlighting its robustness and versatility.
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