Suche: chain of thought

520 Paper gefunden.

• TabRank: Chain-of-Thought Distillation for Table Re-Rankers

  Adarsh Singh, Kushal Raj Bhandari, Jianxi Gao, Soham Dan, Vivek Gupta · 29. Juli 2026 · Information Retrieval and Search Behavior

  The ability to retrieve relevant tables for answering questions is a key task for structured information retrieval. Multi-stage retrieval systems rely heavily on rerankers to refine candidate lists produced by efficient first-stage retrievers. As a result, neural rerankers and LLM-based reranking me…

• CoTinyVLA: Chain-of-Thought Distillation for a Sub-Billion-Parameter Vision-Language-Action Model

  Minhyeok Lee, Chiyoung Kim, Chanhoe Gu, Seongrok Kim, Sanghyuk Roy Choi, Donghwan Hwang, Donghun Ryu, Seokhyun Kim · 29. Juli 2026 · Multimodal Machine Learning Applications

  Vision-Language-Action (VLA) models translate natural-language commands into robot action sequences, but leading systems on the LIBERO-Plus robustness benchmark use three- to seven-billion-parameter backbones whose memory demands can exceed embedded robotic budgets. We present CoTinyVLA, a 0.9B-para…

• Reasoning to Regulate: Chain-of-Thought for Traffic Rule Understanding

  Yueru Luo, Xu Yan, Changqing Zhou, Yiming Yang, Chao Zhan, Shuqi Mei, Chao Zheng, Zhen Li · 28. Juli 2026 · Multimodal Machine Learning Applications

  Understanding and complying with traffic regulations is a safety-critical requirement for autonomous driving, yet remains challenging due to the diversity and context dependence of traffic signage. Importantly, regulation understanding is not a simple recognition task, but a reasoning problem: wheth…

• Two Regimes of Chain-of-Thought Unfaithfulness: Behavioral Detection Fails Where Models Are Wrong

  Suramya R. Angdembay, Dikshant Aryal, Nick Rahimi · 28. Juli 2026 · Embodied and Extended Cognition

  Chain-of-thought (CoT) explanations support oversight only if they are faithful: the stated reasoning must actually produce the answer. Auditing black-box (behavioral) detection of unfaithful CoT against FaithCoT-Bench's human annotations, we find answer correctness structures the problem at every l…

• Loong: Synthesize Long Chain-of-Thoughts at Scale through Verifiers

  Xingyue Huang, Rishabh, Gregor Franke, Ziyi Yang, Jiamu Bai, Weijie Bai, Jinhe Bi, Zifeng Ding, Yiqun Duan, Chengyu Fan, Wendong Fan, Xin Gao, Ruohao Guo, Yuan He, Zhuangzhuang He, Xianglong Hu, Neil Johnson, Bowen Li, Fangru Lin, Siyu Lin, Tong Liu, Yunpu Ma, Hao Shen, Hao Sun, Beibei Wang, Fangyijie Wang, Hao Wang, Haoran Wang, Yang Wang, Yifeng Wang, Zhaowei Wang, Ziyang Wang, Yifan Wu, Zikai Xiao, Chengxing Xie, Fan Yang, Junxiao Yang, Qianshuo Ye, Ziyu Ye, Guangtao Zeng, Yuwen Ebony Zhang, Zeyu Zhang, Zihao Zhu, Bernard Ghanem, Philip Torr, Guohao Li · 28. Juli 2026 · Large Language Models

  Recent advances in Large Language Models (LLMs) have shown that their reasoning capabilities can be significantly improved through Reinforcement Learning with Verifiable Reward (RLVR), particularly in domains like mathematics and programming, where ground-truth correctness can be automatically evalu…

• Not All LLM Reasoning is Visible in the Chain-of-Thought

  Vatsal Baherwani, Tom Goldstein, Ashwinee Panda · 28. Juli 2026 · Adversarial Robustness in Machine Learning

  A key question for AI safety is whether a language model expresses all of its reasoning in its output tokens. We demonstrate a concrete failure mode where frontier models exhibit invisible reasoning by leveraging semantically irrelevant filler tokens to improve performance on synthetic reasoning tas…

• Visual Saliency Steering Distillation for Multimodal Chain-of-Thought Reasoning

  Hao Yang, Jin Wang, Xuejie Zhang · 27. Juli 2026 · Multimodal Machine Learning Applications

  Multimodal chain-of-thought (CoT) reasoning integrates visual and textual cues through step-by-step inference. In small models with limited token budgets, modality-interaction fusion often suppresses tiny cross-modal differences. In particular, multimodal CoT often struggles when different images pa…

• J-CoT: Chain-of-Thought in J-Space

  Junde Wu, Jiayuan Zhu, Fengling Liu, Minhao Hu, Jiazhen Pan · 27. Juli 2026 · Large Language Models

  Chain-of-thought prompting improves language-model reasoning by carrying intermediate states across successive computation steps. However, relying on natural language as the only recurrent interface is overly restrictive, since many transient computations do not need to be fully verbalized. Existing…

• Chemical Chain-of-Thought Functions as a Hallucination-Prone Molecular Scratchpad

  Jiatong Li, Yuxuan Ren, Weida Wang, Xiaoyong Wei, Yatao Bian · 24. Juli 2026 · Neurobiology of Language and Bilingualism

  Chemical reasoning language models are expected to derive molecular answers through faithful chain-of-thought (CoT). However, across four reasoning model families and twelve chemistry tasks, hallucination is widespread and largely decoupled from answer correctness: correct answers often coexist with…

• REFACT: Adaptive Fact Restatement for Compact and Faithful Chain-of-Thought Reasoning

  Zhensheng Jin, Xin Dai, Zhenghao Liu, Chaojun Xiao, Huiyuan Xie, Yu Gu, Ge Yu, Maosong Sun · 24. Juli 2026 · Large Language Models

  Large Language Models (LLMs) increasingly leverage long-form reasoning to solve complex tasks, yet their reasoning processes can deviate from the provided context when evidence is incomplete, noisy, or conflicts with parametric knowledge. Existing grounding approaches either append citations after g…

• Token Budget Saturation and Mechanistic Early Detection of Reasoning Non-Convergence in Chain-of-Thought Models

  Renuka Oladri, Niveda Jawahar, Abdirisak Mohamed · 24. Juli 2026 · Paranormal Experiences and Beliefs

  Chain-of-thought reasoning models such as DeepSeek-R1-Distill-Qwen-7B exhibit a bimodal convergence pattern: generations either terminate within a token budget (converged) or exhaust it without reaching a conclusion (non-converged). We characterize this phenomenon empirically, showing that converged…

• Is MoE Routing a Huffman Code? Discovering the Frequency-Diversity Law in Chain-of-Thought

  Ching-Chieh Tsao, Zhuoyi Lin, Wenya Wang · 24. Juli 2026 · Software Engineering Research

  Mixture-of-Experts architectures have revolutionized scaling, yet the underlying logic of their routing remains a black box. In this paper, we uncover a fundamental governing principle: MoE routing is not merely selection, but a manifestation of Huffman Coding. We introduce the Frequency-Diversity L…

• CASE: Causal Alignment and Structural Enforcement for Improving Chain-of-Thought Faithfulness

  Ziming Wang, Yinghua Yao, Changwu Huang, Ke Tang, Xin Yao · 22. Juli 2026 · Large Language Models

  Chain-of-thought (CoT) reasoning is widely used to improve both the performance and interpretability of large language models (LLMs), yet the generated reasoning may not faithfully support the final answer. We study this problem from a causal perspective, where a faithful CoT process should follow t…

• Training Continuous Chain of Thought Models: A Tale of Two Regimes

  Varun Yerram, He He, Eunsol Choi · 21. Juli 2026 · Multimodal Machine Learning Applications

  Continuous Chain-of-Thought methods replace verbose reasoning traces with a short sequence of dense latent representations. Earlier continuous CoT methods indirectly supervise the latent representations such that its final state match that of verbose reasoning traces, requiring autoregressive, slow …

• Answer-Conditioned Chains of Thought Degrade Verifiable-Reasoning Distillation in Large Language Models

  Jungseob Lee, Seungyoon Lee, Suhyune Son, Dongyub Jude Lee, Sungbin Han, Sugyeong Eo, Heuiseok Lim · 17. Juli 2026 · Large Language Models

  A standard recipe for distilling the reasoning ability of large language models (LLMs) is to sample chains of thought from the model, keep those that reach the correct final answer, and fine-tune on the survivors. When sampling fails, a common fix shows the generator the gold answer and asks it to w…

• Interventional Grounding Audits: Black-Box Premise-Dependency Tests for LLM Chain-of-Thought via Predicate Substitution

  Hironao Nakamura · 16. Juli 2026 · Artificial Intelligence in Healthcare and Education

  Large language models produce chain-of-thought (CoT) reasoning that appears logically sound yet may not genuinely depend on its stated premises. We introduce interventional grounding audits, a black-box, step-level test of premise dependency: we intervene on a single premise by substituting its targ…

• Parse, Search, and Confirmation: Training-Free Aerial Vision-and-Dialog Navigation with Chain-of-Thought Reasoning and Structured Spatial Memory

  Yu Qi, Hongyu Li, Shaofei Huang, Tianrui Hui, Yaxiong Wang, Lechao Cheng, Zhun Zhong, Si Liu, Meng Wang · 14. Juli 2026 · Multimodal Machine Learning Applications

  In this paper, we tackle the Aerial Vision-and-Dialog Navigation (AVDN) task in the training-free setting for resource-efficient high-altitude UAV navigation.Naively applying MLLMs leads to unreliable navigation due to weak directional grounding and the lack of explicit spatial memory.To address the…

• The Cost of Reasoning: Chain-of-Thought Induces Overconfidence in Vision-Language Models

  Robert Welch, Emir Konuk, Kevin Smith · 14. Juli 2026 · Multimodal Machine Learning Applications

  Vision-language models (VLMs) are increasingly deployed in high-stakes settings where reliable uncertainty quantification (UQ) is as important as predictive accuracy. Extended reasoning via chain-of-thought (CoT) prompting or reasoning-trained models has become ubiquitous in modern VLM pipelines, ye…

• Answer-Conditioned Chain-of-Thought Distillation for Few-Shot Industrial Vision with Small VLMs

  Shubham Rao · 14. Juli 2026 · Multimodal Machine Learning Applications

  Deploying AI-based visual inspection in manufacturing is hard because requirements change often, new defect types appear, and large labeled datasets are rarely available. We propose answer-conditioned chain-of-thought (CoT) distillation for rapidly adapting small vision-language models (VLMs) to new…

• Valid $\ne$ Necessary: Diagnosing Latent Inefficiency in Chain-of-Thought

  Daeyeop Lee, Hwanjo Yu · 14. Juli 2026 · Large Language Models

  Chain-of-Thought (CoT) prompting has significantly advanced the reasoning capabilities of Large Language Models (LLMs), yet it often incurs substantial computational costs due to over-reasoning: the generation of redundant, verbose, or irrelevant steps. While existing reasoning step evaluators effec…

• OS-Pruner: Pruning Chains-of-Thought of Reasoning Models via Optimal Stopping

  Mohammed Ehab, Aymane El Gadarri, Vivek F. Farias, Adam Jozefiak, Ciamac C. Moallemi · 14. Juli 2026 · Large Language Models

  Large Language Models (LLMs) have achieved remarkable success in complex reasoning tasks through Chain-of-Thought (CoT) prompting. However, these models often exhibit "computational overthinking," generating redundant reasoning steps that increase latency and cost without improving accuracy. Recent …

• Length Penalties Make Chain-of-Thought Less Monitorable

  Bryce Little · 14. Juli 2026 · Large Language Models

  Length-penalized reinforcement learning can shorten chain-of-thought reasoning while hiding an influence that drives the model's answer. In our experiments, training with length penalties does not stop misleading hints from steering models, even though the models' chains of thought mention the hint …

• The Optimal Sample Complexity of Learning Autoregressive Chain-of-Thought

  Zhiyuan Li · 9. Juli 2026 · Machine Learning and Algorithms

  We prove that, in the realizable PAC setting, the sample complexity of exact-trace learning for full autoregressive Chain-of-Thought traces is upper bounded by the standard multiclass rate of the local next-token class, where this rate is governed by the Daniely--Shalev-Shwartz dimension. Under exac…

• Reasoning Consistency Scanning: A Framework for Auditing Chain-of-Thought Validity in AI Safety Evaluations

  Silvia Santano · 9. Juli 2026 · Adversarial Robustness in Machine Learning

  Prior work has shown that chain-of-thought (CoT) reasoning is often unfaithful: a model's stated reasoning does not reliably reflect the process that produced its output. Detecting unfaithfulness, though, requires controlled experimental interventions, which cannot be applied to evaluation transcrip…

• EventCoT: Event-centric Video Chain-of-thought for Reasoning Temporal Localization

  Youngkil Song, Yoonjae Baek, Dongwon Kim, Inho Kim, Dongkeun Kim, Suha Kwak · 7. Juli 2026 · Multimodal Machine Learning Applications

  Reasoning temporal localization (RTL) requires a model to generate an answer that itself contains the time interval supporting it, so high-level reasoning and precise temporal grounding must be produced jointly in a single response. To tackle this challenging task, we propose the first event-centric…