Búsqueda: chain of thought

520 artículos encontrados.

• SceneCOT: Eliciting Grounded Chain-of-Thought Reasoning in 3D Scenes

  Xiongkun Linghu, Jiangyong Huang, Ziyu Zhu, Baoxiong Jia, Siyuan Huang · 6 de marzo de 2026 · Multimodal Machine Learning Applications

  Existing research on 3D Large Language Models (LLMs) still struggles to achieve grounded question-answering, primarily due to the under-exploration of the mechanism of human-like scene-object grounded reasoning. This paper bridges the gap by presenting a novel framework. We first introduce a grounde…

• Reasoning Theater: Disentangling Model Beliefs from Chain-of-Thought

  Siddharth Boppana, Annabel Ma, Max Loeffler, Raphael Sarfati, Eric Bigelow, Atticus Geiger, Owen Lewis, Jack Merullo · 6 de marzo de 2026 · Embodied and Extended Cognition

  We provide evidence of performative chain-of-thought (CoT) in reasoning models, where a model becomes strongly confident in its final answer, but continues generating tokens without revealing its internal belief. Our analysis compares activation probing, early forced answering, and a CoT monitor acr…

• C2-Faith: Benchmarking LLM Judges for Causal and Coverage Faithfulness in Chain-of-Thought Reasoning

  Avni Mittal, Rauno Arike · 6 de marzo de 2026 · Explainable Artificial Intelligence (XAI)

  Large language models (LLMs) are increasingly used as judges of chain-of-thought (CoT) reasoning, but it remains unclear whether they can reliably assess process faithfulness rather than just answer plausibility. We introduce C2-Faith, a benchmark built from PRM800K that targets two complementary di…

• Online Learnability of Chain-of-Thought Verifiers: Soundness and Completeness Trade-offs

  Maria-Florina Balcan, Avrim Blum, Kiriaki Fragkia, Zhiyuan Li, Dravyansh Sharma · 5 de marzo de 2026 · Machine Learning and Algorithms

  Large language models with chain-of-thought generation have demonstrated great potential for producing complex mathematical proofs. However, their reasoning can often go astray, leading to increasing interest in formal and learned verifiers. A major challenge in learning verifiers, especially when t…

• Think-as-You-See: Streaming Chain-of-Thought Reasoning for Large Vision-Language Models

  Jialiang Zhang, Junlong Tong, Junyan Lin, Hao Wu, Yirong Sun, Yunpu Ma, Xiaoyu Shen · 4 de marzo de 2026 · Multimodal Machine Learning Applications

  Large Vision Language Models (LVLMs) exhibit strong Chain-of-Thought (CoT) capabilities, yet most existing paradigms assume full-video availability before inference, a batch-style process misaligned with real-world video streams where information arrives sequentially. Motivated by the streaming natu…

• When does Chain-of-Thought Help: A Markovian Perspective

  Zihan Wang, Yijun Dong, Qi Lei · 3 de marzo de 2026 · Embodied and Extended Cognition

  Chain-of-Thought (CoT) prompting is a widely used inference-time technique for improving reasoning, yet its gains are uneven across tasks. We analyze when and why CoT helps by modeling the step-wise reasoning trajectory as a Markov chain. Each intermediate step is a state and the dependence between …

• FaithCoT-Bench: Benchmarking Instance-Level Faithfulness of Chain-of-Thought Reasoning

  Xu Shen, Song Wang, Zhen Tan, Laura Yao, Xinyu Zhao, Kaidi Xu, Xin Wang, Tianlong Chen · 3 de marzo de 2026 · Religion, Spirituality, and Psychology

  Large language models (LLMs) increasingly rely on Chain-of-Thought (CoT) prompting to improve problem-solving and provide seemingly transparent explanations. However, growing evidence shows that CoT often fail to faithfully represent the underlying reasoning process, raising concerns about their rel…

• Reason Like a Radiologist: Chain-of-Thought and Reinforcement Learning for Verifiable Report Generation

  Peiyuan Jing, Kinhei Lee, Zhenxuan Zhang, Huichi Zhou, Zhengqing Yuan, Zhifan Gao, Lei Zhu, Giorgos Papanastasiou, Yingying Fang, Guang Yang · 3 de marzo de 2026 · Multimodal Machine Learning Applications

  Radiology report generation is critical for efficiency but current models lack the structured reasoning of experts, hindering clinical trust and explainability by failing to link visual findings to precise anatomical locations. This paper introduces BoxMed-RL, a groundbreaking unified training frame…

• ClinCoT: Clinical-Aware Visual Chain-of-Thought for Medical Vision Language Models

  Xiwei Liu, Yulong Li, Xinlin Zhuang, Xuhui Li, Jianxu Chen, Haolin Yang, Imran Razzak, Yutong Xie · 3 de marzo de 2026 · Multimodal Machine Learning Applications

  Medical Vision-Language Models have shown promising potential in clinical decision support, yet they remain prone to factual hallucinations due to insufficient grounding in localized pathological evidence. Existing medical alignment methods primarily operate at the response level through preference …

• Stepwise Penalization for Length-Efficient Chain-of-Thought Reasoning

  Xintong Li, Sha Li, Rongmei Lin, Hongye Jin, Linwei Li, Hejie Cui, Sarah Zhang, Chia-Yuan Chang, Kewei Cheng, Besnik Fetahu, Priyanka Nigam, Jingbo Shang, Bing Yin · 3 de marzo de 2026 · Reinforcement Learning in Robotics

  Large reasoning models improve with more test-time computation, but often overthink, producing unnecessarily long chains-of-thought that raise cost without improving accuracy. Prior reinforcement learning approaches typically rely on a single outcome reward with trajectory-level length penalties, wh…

• Multimodal Modular Chain of Thoughts in Energy Performance Certificate Assessment

  Zhen Peng, Peter J. Bentley · 3 de marzo de 2026 · Building Energy and Comfort Optimization

  Accurate evaluation of building energy performance remains challenging in regions where scalable Energy Performance Certificate (EPC) assessments are unavailable. This paper presents a cost-efficient framework that leverages Vision-Language models for automated EPC pre-assessment from limited visual…

• Decoding Answers Before Chain-of-Thought: Evidence from Pre-CoT Probes and Activation Steering

  Kyle Cox, Darius Kianersi, Adri\`a Garriga-Alonso · 3 de marzo de 2026 · Explainable Artificial Intelligence (XAI)

  As chain-of-thought (CoT) has become central to scaling reasoning capabilities in large language models (LLMs), it has also emerged as a promising tool for interpretability, suggesting the opportunity to understand model decisions through verbalized reasoning. However, the utility of CoT toward inte…

• Draft-Thinking: Learning Efficient Reasoning in Long Chain-of-Thought LLMs

  Jie Cao, Tianwei Lin, Zhenxuan Fan, Bo Yuan, Ziyuan Zhao, Rolan Yan, Wenqiao Zhang, Siliang Tang · 3 de marzo de 2026 · Logic, Reasoning, and Knowledge

  Long chain-of-thought~(CoT) has become a dominant paradigm for enhancing the reasoning capability of large reasoning models~(LRMs); however, the performance gains often come with a substantial increase in reasoning budget. Recent studies show that existing CoT paradigms tend to induce systematic ove…

• Generative Visual Chain-of-Thought for Image Editing

  Zijin Yin, Tiankai Hang, Yiji Cheng, Shiyi Zhang, Runze He, Yu Xu, Chunyu Wang, Bing Li, Zheng Chang, Kongming Liang, Qinglin Lu, Zhanyu Ma · 3 de marzo de 2026 · Multimodal Machine Learning Applications

  Existing image editing methods struggle to perceive where to edit, especially under complex scenes and nuanced spatial instructions. To address this issue, we propose Generative Visual Chain-of-Thought (GVCoT), a unified framework that performs native visual reasoning by first generating spatial cue…

• Thinking with Images as Continuous Actions: Numerical Visual Chain-of-Thought

  Kesen Zhao, Beier Zhu, Junbao Zhou, Xingyu Zhu, Zhongqi Yue, Hanwang Zhang · 2 de marzo de 2026 · Multimodal Machine Learning Applications

  Recent multimodal large language models (MLLMs) increasingly rely on visual chain-of-thought to perform region-grounded reasoning over images. However, existing approaches ground regions via either textified coordinates-causing modality mismatch and semantic fragmentation or fixed-granularity patche…

• TCM-DiffRAG: Personalized Syndrome Differentiation Reasoning Method for Traditional Chinese Medicine based on Knowledge Graph and Chain of Thought

  Jianmin Li, Ying Chang, Su-Kit Tang, Yujia Liu, Yanwen Wang, Shuyuan Lin, Binkai Ou · 27 de febrero de 2026 · Traditional Chinese Medicine Studies

  Background: Retrieval augmented generation (RAG) technology can empower large language models (LLMs) to generate more accurate, professional, and timely responses without fine tuning. However, due to the complex reasoning processes and substantial individual differences involved in traditional Chine…

• D-COT: Disciplined Chain-of-Thought Learning for Efficient Reasoning in Small Language Models

  Shunsuke Ubukata · 26 de febrero de 2026 · Large Language Models

  Chain-of-Thought (CoT) distillation from Large Language Models (LLMs) often induces "overthinking" in Small Language Models (SLMs), leading to performance degradation and excessive token consumption. In this study, we propose Disciplined Chain-of-Thought (D-CoT), a novel framework that enforces a st…

• E-comIQ-ZH: A Human-Aligned Dataset and Benchmark for Fine-Grained Evaluation of E-commerce Posters with Chain-of-Thought

  Meiqi Sun, Mingyu Li, Junxiong Zhu · 26 de febrero de 2026 · Large Language Models

  Generative AI is widely used to create commercial posters. However, rapid advances in generation have outpaced automated quality assessment. Existing models emphasize generic esthetics or low level distortions and lack the functional criteria required for e-commerce design. It is especially challeng…

• Counterfactual Simulation Training for Chain-of-Thought Faithfulness

  Peter Hase, Christopher Potts · 25 de febrero de 2026 · Explainable Artificial Intelligence (XAI)

  Inspecting Chain-of-Thought reasoning is among the most common means of understanding why an LLM produced its output. But well-known problems with CoT faithfulness severely limit what insights can be gained from this practice. In this paper, we introduce a training method called Counterfactual Simul…

• Verifying Chain-of-Thought Reasoning via Its Computational Graph

  Zheng Zhao, Yeskendir Koishekenov, Xianjun Yang, Naila Murray, Nicola Cancedda · 24 de febrero de 2026 · Embodied and Extended Cognition

  Current Chain-of-Thought (CoT) verification methods predict reasoning correctness based on outputs (black-box) or activations (gray-box), but offer limited insight into why a computation fails. We introduce a white-box method: Circuit-based Reasoning Verification (CRV). We hypothesize that attributi…

• To Reason or Not to: Selective Chain-of-Thought in Medical Question Answering

  Zaifu Zhan, Min Zeng, Shuang Zhou, Yiran Song, Xiaoyi Chen, Yu Hou, Yifan Wu, Yang Ruan, Rui Zhang · 24 de febrero de 2026 · Large Language Models

  Objective: To improve the efficiency of medical question answering (MedQA) with large language models (LLMs) by avoiding unnecessary reasoning while maintaining accuracy. Methods: We propose Selective Chain-of-Thought (Selective CoT), an inference-time strategy that first predicts whether a questi…

• Analyzing and Improving Chain-of-Thought Monitorability Through Information Theory

  Usman Anwar, Tim Bakker, Dana Kianfar, Cristina Pinneri, Christos Louizos · 23 de febrero de 2026 · Software Testing and Debugging Techniques

  Chain-of-thought (CoT) monitors are LLM-based systems that analyze reasoning traces to detect when outputs may exhibit attributes of interest, such as test-hacking behavior during code generation. In this paper, we use information-theoretic analysis to show that non-zero mutual information between C…

• Curriculum Learning for Efficient Chain-of-Thought Distillation via Structure-Aware Masking and GRPO

  Bowen Yu, Maolin Wang, Sheng Zhang, Binhao Wang, Yi Wen, Jingtong Gao, Bowen Liu, Zimo Zhao, Wanyu Wang, Xiangyu Zhao · 23 de febrero de 2026 · Large Language Models

  Distilling Chain-of-Thought (CoT) reasoning from large language models into compact student models presents a fundamental challenge: teacher rationales are often too verbose for smaller models to faithfully reproduce. Existing approaches either compress reasoning into single-step, losing the interpr…

• BLM-Guard: Explainable Multimodal Ad Moderation with Chain-of-Thought and Policy-Aligned Rewards

  Yiran Yang, Zhaowei Liu, Yuan Yuan, Yukun Song, Xiong Ma, Yinghao Song, Xiangji Zeng, Lu Sun, Yulu Wang, Hai Zhou, Shuai Cui, Zhaohan Gong, Jiefei Zhang · 23 de febrero de 2026 · Multimodal Machine Learning Applications

  Short-video platforms now host vast multimodal ads whose deceptive visuals, speech and subtitles demand finer-grained, policy-driven moderation than community safety filters. We present BLM-Guard, a content-audit framework for commercial ads that fuses Chain-of-Thought reasoning with rule-based poli…

• Evaluating Chain-of-Thought Reasoning through Reusability and Verifiability

  Shashank Aggarwal, Ram Vikas Mishra, Amit Awekar · 20 de febrero de 2026 · Mobile Crowdsensing and Crowdsourcing

  In multi-agent IR pipelines for tasks such as search and ranking, LLM-based agents exchange intermediate reasoning in terms of Chain-of-Thought (CoT) with each other. Current CoT evaluation narrowly focuses on target task accuracy. However, this metric fails to assess the quality or utility of the r…