Suche: chain of thought

520 Paper gefunden.

• Is Chain-of-Thought Really Not Explainability? Chain-of-Thought Can Be Faithful without Hint Verbalization

  Kerem Zaman, Shashank Srivastava · 30. Dezember 2025 · Explainable Artificial Intelligence (XAI)

  Recent work, using the Biasing Features metric, labels a CoT as unfaithful if it omits a prompt-injected hint that affected the prediction. We argue this metric confuses unfaithfulness with incompleteness, the lossy compression needed to turn distributed transformer computation into a linear natural…

• Revisiting Chain-of-Thought Reasoning under Limited Supervision: Semi-supervised Chain-of-Thought Learning

  Hongyang He, Jiuming Liu, Victor Sanchez · 3. Juli 2026 · Large Language Models

  Chain-of-thought (CoT) reasoning has emerged as an effective approach for activating latent reasoning capabilities in large language models. However, most existing CoT methods use reasoning chains mainly as inference-time prompts, while the generated reasoning traces are rarely reused as semi-superv…

• Hidden in Thought: Transferable Chain-of-Thought Artifacts Induce Harmful Behavior

  Ali khalil, Aly M. Kassem, Mohamed Abdelrazek, Santu Rana, Negar Rostamzadeh, Golnoosh Farnadi · 20. Juli 2026 · Adversarial Robustness in Machine Learning

  We investigate whether harmful chain-of-thought (CoT) traces from compromised language models can transfer unsafe behaviour and be distilled into reusable jailbreak attacks. Using an emergent-misalignment organism and a refusal-ablated jailbroken organism, we transplant harmful CoTs into $29$ open-s…

• Better Eyes, Better Thoughts: Why Vision Chain-of-Thought Fails in Medicine

  Yuan Wu, Zongxian Yang, Jiayu Qian, Songpan Gao, Guanxing Chen, Qiankun Li, Yu-An Huang, Zhi-An Huang · 13. April 2026 · Multimodal Machine Learning Applications

  Large vision-language models (VLMs) often benefit from chain-of-thought (CoT) prompting in general domains, yet its efficacy in medical vision-language tasks remains underexplored. We report a counter-intuitive trend: on medical visual question answering, CoT frequently underperforms direct answerin…

• Render-of-Thought: Rendering Textual Chain-of-Thought as Images for Visual Latent Reasoning

  Yifan Wang, Shiyu Li, Peiming Li, Xiaochen Yang, Yang Tang, Zheng Wei · 22. Januar 2026 · Multimodal Machine Learning Applications

  Chain-of-Thought (CoT) prompting has achieved remarkable success in unlocking the reasoning capabilities of Large Language Models (LLMs). Although CoT prompting enhances reasoning, its verbosity imposes substantial computational overhead. Recent works often focus exclusively on outcome alignment and…

• Altered Thoughts, Altered Actions: Probing Chain-of-Thought Vulnerabilities in VLA Robotic Manipulation

  Tuan Duong Trinh, Naveed Akhtar, Basim Azam · 16. März 2026 · Adversarial Robustness in Machine Learning

  Recent Vision-Language-Action (VLA) models increasingly adopt chain-of-thought (CoT) reasoning, generating a natural-language plan before decoding motor commands. This internal text channel between the reasoning module and the action decoder has received no adversarial scrutiny. We ask: which proper…

• Mind the Gap: Bridging Thought Leap for Improved Chain-of-Thought Tuning

  Haolei Xu, Yuchen Yan, Yongliang Shen, Wenqi Zhang, Guiyang Hou, Shengpei Jiang, Kaitao Song, Weiming Lu, Jun Xiao, Yueting Zhuang · 1. Dezember 2025 · Large Language Models

  Large language models (LLMs) have achieved remarkable progress on mathematical tasks through Chain-of-Thought (CoT) reasoning. However, existing mathematical CoT datasets often suffer from Thought Leaps due to experts omitting intermediate steps, which negatively impacts model learning and generaliz…

• Fragile Thoughts: How Large Language Models Handle Chain-of-Thought Perturbations

  Ashwath Vaithinathan Aravindan, Mayank Kejriwal · 5. März 2026 · Ethics and Social Impacts of AI

  Chain-of-Thought (CoT) prompting has emerged as a foundational technique for eliciting reasoning from Large Language Models (LLMs), yet the robustness of this approach to corruptions in intermediate reasoning steps remains poorly understood. This paper presents a comprehensive empirical evaluation o…

• Thought Purity: A Defense Framework For Chain-of-Thought Attack

  Zihao Xue, Zhen Bi, Long Ma, Zhenlin Hu, Yan Wang, Xueshu Chen, Zhenfang Liu, Kang Zhao, Jie Xiao, Jungang Lou · 13. Februar 2026 · Mental Health Research Topics

  Large Reasoning Models (LRMs) leverage Chain-of-Thought (CoT) reasoning to solve complex tasks, but this explicit reasoning process introduces a critical vulnerability: adversarial manipulation of the thought chain itself, known as Chain-of-Thought Attacks (CoTA). Such attacks subtly corrupt the rea…

• Shape of Thought: Progressive Object Assembly via Visual Chain-of-Thought

  Yu Huo, Siyu Zhang, Kun Zeng, Haoyue Liu, Owen Lee, Junlin Chen, Yuquan Lu, Yifu Guo, Yaodong Liang, Xiaoying Tang · 30. Januar 2026 · 3D Shape Modeling and Analysis

  Multimodal models for text-to-image generation have achieved strong visual fidelity, yet they remain brittle under compositional structural constraints, notably generative numeracy, attribute binding, and part-level relations. To address these challenges, we propose Shape-of-Thought (SoT), a visual …

• The Molecular Structure of Thought: Mapping the Topology of Long Chain-of-Thought Reasoning

  Qiguang Chen, Yantao Du, Ziniu Li, Jinhao Liu, Songyao Duan, Jiarui Guo, Minghao Liu, Jiaheng Liu, Tong Yang, Ge Zhang, Libo Qin, Wanxiang Che, Wenhao Huang · 12. Januar 2026 · Machine Learning in Materials Science

  Large language models (LLMs) often fail to learn effective long chain-of-thought (Long CoT) reasoning from human or non-Long-CoT LLMs imitation. To understand this, we propose that effective and learnable Long CoT trajectories feature stable molecular-like structures in unified view, which are forme…

• Thoughts-as-Planning: Latent World Models for Chain-of-Thoughts Optimization via Reinforcement Planning

  Dong Liu, Yanxuan Yu, Ying Nian Wu · 29. Mai 2026 · Multimodal Machine Learning Applications

  The success of large language models (LLMs) across diverse NLP tasks has elevated the importance of reasoning chain optimization as a critical step in aligning model behavior with task objectives. Existing reasoning chain tuning methods often rely on black-box heuristics or gradient-free search, whi…

• Thought-Transfer: Indirect Targeted Poisoning Attacks on Chain-of-Thought Reasoning Models

  Harsh Chaudhari, Ethan Rathbum, Hanna Foerster, Jamie Hayes, Matthew Jagielski, Milad Nasr, Ilia Shumailov, Alina Oprea · 28. Januar 2026 · Large Language Models

  Chain-of-Thought (CoT) reasoning has emerged as a powerful technique for enhancing large language models' capabilities by generating intermediate reasoning steps for complex tasks. A common practice for equipping LLMs with reasoning is to fine-tune pre-trained models using CoT datasets from public r…

• Every Token Leaves a Ripple in the Stream of Thought: Eliciting Model-Internal Token Saliency for Chain-of-Thought Compression

  Tianyi Zhao, Yinhan He, Wendy Zheng, Chen Chen · 1. September 2026 · Large Language Models

  Chain-of-thought (CoT) reasoning improves multi-step problem solving, but long reasoning traces inflate inference cost. Token-level CoT compression reduces this cost by pruning full reasoning chains into shorter traces for model adaptation, making token selection the central challenge. Existing meth…

• Training Multimodal Large Reasoning Models Needs Better Thoughts: A Three-Stage Framework for Long Chain-of-Thought Synthesis and Selection

  Yizhi Wang, Linan Yue, Min-Ling Zhang · 23. Dezember 2025 · Multimodal Machine Learning Applications

  Large Reasoning Models (LRMs) have demonstrated remarkable performance on complex reasoning tasks through long Chain-of-Thought (CoT) reasoning. Extending these successes to multimodal reasoning remains challenging due to the increased complexity of integrating diverse input modalities and the scarc…

• On the Chain-of-Thought Monitorability of Looped Language Models

  Han Wang, Ishwar B Balappanawar, Huan Zhang · 5. Oktober 2026 · Scientific Research and Philosophical Inquiry

  Chain-of-thought (CoT) monitoring provides a promising approach for detecting undesirable model behavior. Looped language models (LoopLMs) repeatedly apply shared transformer layers, increasing effective computational depth and enabling additional latent computation without increasing model size. Ho…

• When Reasoning Helps Action: Monitoring and Steering Chain-of-Thought in Vision-Language-Action Policies

  Sathwik Karnik, Joseph JR. Lee, Aryaman Gupta, Somil Bansal · 2. Oktober 2026 · Semantic Web and Ontologies

  Reasoning-enabled VLA policies expose chain-of-thought (CoT) traces that appear to explain and guide their actions, creating a potential interface for runtime safety through reasoning monitoring and correction. In this work, we define and operationalize two evaluation axes for assessing when this in…

• Structure vs. Chain-of-Thought: Evaluating LLM Criteria Extraction for Depression Severity

  Xinkai Chen · 1. Oktober 2026 · Mental Health via Writing

  A large language model (LLM) can rate depression severity directly from a social media post or mark which clinical criteria the post shows and let code turn the count into a label. The latter is easier to audit because a clinician can check each marked criterion. We compare these approaches on two R…

• DuraS2ST: Chain-of-Thought and Reinforcement Learning for Duration-Aligned Speech-to-Speech Translation

  Yayue Deng, Dingdong Wang, Yuxuan Hu, Jinyu Li, Yanqing Liu, Yuanyuan Wang, Weidong Chen, Helen M. Meng, Shujie Liu, Xixin Wu · 30. September 2026 · Speech Recognition and Synthesis

  Speech-to-speech translation (S2ST) in time-sensitive applications such as video dubbing requires not only semantic fidelity and speaker preservation, but also strict duration consistency to avoid audio-visual misalignment. However, existing S2ST systems largely generate target speech without explic…

• Correct Answers, Invalid Traces: What Verifiable Grade-School Math Reveals About Chain-of-Thought Traces

  Ratish Puduppully, Pranabendu Misra, Paarth Iyer, Durgesh Kalwar, Vardhan Palod, Subbarao Kambhampati · 30. September 2026 · Semantic Web and Ontologies

  Chain-of-thought traces are widely read as records of how models reach their answers, informing debugging, agent auditing, and claims about reasoning. Testing this interpretation is difficult because natural-language thinking traces are rarely mechanically verifiable. We revisit it in iGSM, a synthe…

• Hidden Reasoning Must Leak, but Need Not Be Readable: Fundamental Opportunities and Limits for Chain-of-Thought Monitoring

  Mohammadali Mohammadkhani, Madhava Krishna, Yash Sarrof, Michael Hahn · 30. September 2026 · Security and Verification in Computing

  Can reasoning models trick chain of thought (CoT) monitors and perform hidden computation without revealing it in their thinking traces? We show that the answer depends on the underlying task difficulty and the model size. Simple computations can be performed covertly; however, beyond a threshold de…

• SpatialSpeak: QA-Native Reconstruction with Local and Global Context for Spatial Chain-of-Thought Reasoning

  Yang Cao, Jiaxin Zhang, Dave Zhenyu Chen, Yingji Zhong, Ruiyuan Gao, Lanqing Hong, Dan Xu · 29. September 2026 · Multimodal Machine Learning Applications

  Vision-language models (VLMs) can benefit from geometric priors for multi-view spatial reasoning, yet answer-only training does not directly supervise the intermediate geometric estimates and their use in deriving quantitative spatial answers. We hypothesize that spatial chain-of-thought (CoT) super…

• Allspark: Weak to Strong Transfer via Alternating Chain of Thought

  Kaizhao Liang, Junxiong Wang, Chen Liang, Zhendong Wang, Qiang Liu · 29. September 2026 · Large Language Models

  Recent progress in frontier models has renewed interest in large-scale reinforcement learning (RL), but the cost of generating large-model rollouts makes even testing RL recipes expensive. We ask whether reasoning improvements learned by a small, weak model can benefit a larger, stronger model witho…

• SeOPD: Self-Evolving LLMs via Online Policy Distillation from Self-Generated Chain-of-Thought

  Xiaoshu Chen, Xiangyu Wong, Sihang Zhou, Ke Liang, Xinwang Liu · 29. September 2026 · Large Language Models

  Recent advances in online policy self-distillation (OPSD) have demonstrated that large language models (LLMs) can improve their capabilities by leveraging external privileged information (PI), such as manual annotations or feedback from external environments. However, obtaining accurate annotations …

• Ceiling of a Task: When Can a Transformer Succeed Without Its Chain of Thought?

  Jiashu He, Jinxuan Fan, Xiao Xiao, Radu Marculescu, Alejandro Ribeiro · 29. September 2026 · Semantic Web and Ontologies

  Reasoning models generate long chains of thought before they answer, yet it is debated whether the content of these chains does real computational work or is largely decorative. We study this question by viewing a transformer as a shallow circuit. One forward pass through a fixed number of layers ha…