Búsqueda: chain of thought

520 artículos encontrados.

• Rethinking Dense Sequential Chains: Reasoning Language Models Can Extract Answers from Sparse, Order-Shuffling Chain-of-Thoughts

  Yi-Chang Chen, Feng-Ting Liao, Da-shan Shiu, Hung-yi Lee · 11 de mayo de 2026 · Large Language Models

  Modern reasoning language models generate dense, sequential chain-of-thought traces implicitly assuming that every token contributes and that steps must be consumed in order. We challenge both assumptions through a systematic intervention pipeline--removal, masking, shuffling, and noise injection--a…

• Reliable Chain-of-Thought via Prefix Consistency

  Naoto Iwase, Yuki Ichihara, Mohammad Atif Quamar, Junpei Komiyama · 11 de mayo de 2026 · Large Language Models

  Large Language Models often improve accuracy on reasoning tasks by sampling multiple Chain-of-Thought (CoT) traces and aggregating them with majority voting (MV), a test-time technique called self-consistency. When we truncate a CoT partway through and regenerate the remainder, we observe that trace…

• The Coupling Tax: How Shared Token Budgets Undermine Visible Chain-of-Thought Under Fixed Output Limits

  Wenhua Nie, Junlin Liu, Jianan Wu, Zijie Meng, Yilong Fan, Zhang Zijian, Haoran Zheng, Jyh-Shing Roger Jang · 11 de mayo de 2026 · Large Language Models

  Chain-of-thought reasoning is often treated as a monotone way to improve language-model accuracy by letting a model think longer. We identify a countervailing effect, the coupling tax: when reasoning traces and final answers share one output-token budget, long traces can crowd out the answer they ar…

• ExpThink: Experience-Guided Reinforcement Learning for Adaptive Chain-of-Thought Compression

  Tingcheng Bian, Yuzhe Zhang, Jing Jin, Jinchang Luo, MingQuan Cheng, Haiwei Wang, Wenyuan Jiang, Miaohui Wang · 11 de mayo de 2026 · Reinforcement Learning in Robotics

  Large reasoning models (LRMs) achieve strong performance via extended chain-of-thought (CoT) reasoning, yet suffer from excessive token consumption and high inference latency. Existing reinforcement learning (RL) approaches for CoT compression rely on uniform, static length penalties that neglect mo…

• Convergence and Emergence of In-Context Reinforcement Learning with Chain of Thought

  Zixuan Xie, Xinyu Liu, Rohan Chandra, Shangtong Zhang · 11 de mayo de 2026 · Reinforcement Learning in Robotics

  In-context reinforcement learning (ICRL) refers to the ability of RL agents to adapt to new tasks at inference time without parameter updates by conditioning on additional context. Recent empirical studies further demonstrate that Chain-of-Thought (CoT) generation can amplify this ICRL capability. T…

• A Theory of Online Learning with Autoregressive Chain-of-Thought Reasoning

  Ilan Doron-Arad, Idan Mehalel, Elchanan Mossel · 11 de mayo de 2026 · Machine Learning and Algorithms

  Autoregressive generation lies at the heart of the mechanism of large language models. It can be viewed as the repeated application of a next-token generator: starting from an input string (prompt), the generator is applied for $M$ steps, and the last generated token is taken as the final output. [J…

• Towards Safer Large Reasoning Models by Promoting Safety Decision-Making before Chain-of-Thought Generation

  Jianan Chen, Zhifang Zhang, Shuo He, Linan Yue, Lei Feng, Minling Zhang · 6 de mayo de 2026 · Autonomous Vehicle Technology and Safety

  Large reasoning models (LRMs) achieved remarkable performance via chain-of-thought (CoT), but recent studies showed that such enhanced reasoning capabilities are at the expense of significantly degraded safety capabilities. In this paper, we reveal that LRMs' safety degradation occurs only after CoT…

• Reasoning Models Can be Accurately Pruned Via Chain-of-Thought Reconstruction

  Ryan Lucas, Kayhan Behdin, Zhipeng Wang, Qingquan Song, Shao Tang, Rahul Mazumder · 6 de mayo de 2026 · Bayesian Modeling and Causal Inference

  Reasoning language models such as DeepSeek-R1 produce long chain-of-thought traces during inference time which make them costly to deploy at scale. We show that using compression techniques such as neural network pruning produces greater performance loss than in typical language modeling tasks, and …

• Imitation Game for Adversarial Disillusion with Chain-of-Thought Reasoning in Generative AI

  Ching-Chun Chang, Fan-Yun Chen, Shih-Hong Gu, Kai Gao, Hanrui Wang, Isao Echizen · 1 de mayo de 2026 · Virtual Reality Applications and Impacts

  As the cornerstone of artificial intelligence, machine perception confronts a fundamental threat posed by adversarial illusions. These adversarial attacks manifest in two primary forms: deductive illusion, where specific stimuli are crafted based on the victim model's general decision logic, and ind…

• CheXthought: A global multimodal dataset of clinical chain-of-thought reasoning and visual attention for chest X-ray interpretation

  Sonali Sharma, Jin Long, George Shih, Sarah Eid, Christian Bluethgen, Francine L. Jacobson, Emily B. Tsai, Global Radiology Consortium, Ahmed M. Alaa, Curtis P. Langlotz · 30 de abril de 2026 · Multimodal Machine Learning Applications

  Chest X-ray interpretation is one of the most frequently performed diagnostic tasks in medicine and a primary target for AI development, yet current vision--language models are primarily trained on datasets of paired images and reports, not the cognitive processes and visual attention that underlie …

• Cheaper, Better, Faster, Stronger: Robust Text-to-SQL without Chain-of-Thought or Fine-Tuning

  Yusuf Denizay D\"onder, Derek Hommel, Andrea W Wen-Yi, David Mimno, Unso Eun Seo Jo · 29 de abril de 2026 · Scientific Computing and Data Management

  LLMs are effective at code generation tasks like text-to-SQL, but is it worth the cost? Many state-of-the-art approaches use non-task-specific LLM techniques including Chain-of-Thought (CoT), self-consistency, and fine-tuning. These methods can be costly at inference time, sometimes requiring over a…

• FGDM: Reasoning Aware Multi-Agentic Framework for Software Bug Detection using Chain of Thought and Tree of Thought Prompting

  Srita Padmanabhuni, Bhargavi Karuturi, Jerusha Karen Indupalli, Santhan Reddy Chilla, Vivek Yelleti · 29 de abril de 2026 · Software Engineering Research

  Deep Learning methods are becoming prominent in automated software bug detection; however, they lack the global understanding of the given code. Consequently, their performance tends to degrade, especially when they are applied to large interconnected code bases or complex modular programs. Recently…

• CAP-CoT: Cycle Adversarial Prompt for Improving Chain of Thoughts in LLM Reasoning

  Shuxu Chen, Yitian Zhou, Jiaquan Zhang, Haoyu Bian, Aming Wu, Sungyoung Lee, Chaoning Zhang, Hyundong Shin · 29 de abril de 2026 · Large Language Models

  Chain-of-Thought (CoT) prompting has emerged as a simple and effective way to elicit step-by-step solutions from large language models (LLMs). However, CoT reasoning can be unstable across runs on long, multi-step problems, leading to inconsistent answers for unchanged task. Most prior work focuses …

• When Chain-of-Thought Fails, the Solution Hides in the Hidden States

  Houman Mehrafarin, Amit Parekh, Ioannis Konstas · 28 de abril de 2026 · Neurobiology of Language and Bilingualism

  Whether intermediate reasoning is computationally useful or merely explanatory depends on whether chain-of-thought (CoT) tokens contain task-relevant information. We present a mechanistic causal analysis of CoT on GSM8K using activation patching: transferring token-level hidden states from a CoT gen…

• Thinking Without Words: Efficient Latent Reasoning with Abstract Chain-of-Thought

  Keshav Ramji, Tahira Naseem, Ramón Fernandez Astudillo · 27 de abril de 2026 · Multimodal Machine Learning Applications

  While long, explicit chains-of-thought (CoT) have proven effective on complex reasoning tasks, they are costly to generate during inference. Non-verbal reasoning methods have emerged with shorter generation lengths by leveraging continuous representations, yet their performance lags behind verbalize…

• Beyond Chain-of-Thought: Rewrite as a Universal Interface for Generative Multimodal Embeddings

  Peixi Wu, Ke Mei, Feipeng Ma, Bosong Chai, Zhibin Lan, Chenxi Zhao, Shannan Yan, Jie Chen, Zhangchi Hu, Yansong Peng, Bo Lin, Junjie Zhou, Dacheng Yin, Tianyi Wang, Fengyun Rao, Jing Lyu, Hebei Li, Xiaoyan Sun · 27 de abril de 2026 · Large Language Models

  Multimodal Large Language Models (MLLMs) have emerged as a promising foundation for universal multimodal embeddings. Recent studies have shown that reasoning-driven generative multimodal embeddings can outperform discriminative embeddings on several embedding tasks. However, Chain-of-Thought (CoT) r…

• VG-CoT: Towards Trustworthy Visual Reasoning via Grounded Chain-of-Thought

  Byeonggeuk Lim, Kyeonghyun Kim, JungMin Yun, YoungBin Kim · 24 de abril de 2026 · Multimodal Machine Learning Applications

  The advancement of Large Vision-Language Models (LVLMs) requires precise local region-based reasoning that faithfully grounds the model's logic in actual visual evidence. However, existing datasets face limitations in scalability due to extensive manual annotation and lack of explicit alignment betw…

• Unlocking Multi-Spectral Data for Multi-Modal Models with Guided Inputs and Chain-of-Thought Reasoning

  Dahun Kim, Ganesh Satish Mallya, Anelia Angelova · 24 de abril de 2026 · Remote-Sensing Image Classification

  Multi-spectral imagery is a valuable input signal for Remote Sensing applications, such as land-use and land-cover classification and environmental monitoring. However, generalist Large Multi-modal Models (LMMs) are typically trained on RGB images, limiting their applicability to the RGB domain. At …

• SurgCoT: Advancing Spatiotemporal Reasoning in Surgical Videos through a Chain-of-Thought Benchmark

  Gui Wang, YongSong Zhou, Kaijun Deng, Wooi Ping Cheah, Rong Qu, Jianfeng Ren, Linlin Shen · 23 de abril de 2026 · Multimodal Machine Learning Applications

  Fine-grained spatiotemporal reasoning on surgical videos is critical, yet the capabilities of Multi-modal Large Language Models (MLLMs) in this domain remain largely unexplored. To bridge this gap, we introduce SurgCoT, a unified benchmark for evaluating chain-of-thought (CoT) reasoning in MLLMs acr…

• Less Languages, Less Tokens: An Efficient Unified Logic Cross-lingual Chain-of-Thought Reasoning Framework

  Chenyuan Zhang, Qiguang Chen, Xie Chen, Zhuotao Tian, Bowen Xing, Meishan Zhang, Libo Qin, Baotian Hu, Min Zhang · 23 de abril de 2026 · Advanced Graph Neural Networks

  Cross-lingual chain-of-thought (XCoT) with self-consistency markedly enhances multilingual reasoning, yet existing methods remain costly due to extensive sampling of full trajectories across languages. Moreover, multilingual LLM representations vary strongly by language, hindering direct feature com…

• Chain-of-Thought as a Lens: Evaluating Structured Reasoning Alignment between Human Preferences and Large Language Models

  Boxuan Wang, Zhuoyun Li, Xinmiao Huang, Xiaowei Huang, Yi Dong · 22 de abril de 2026 · Large Language Models

  This paper primarily demonstrates a method to quantitatively assess the alignment between multi-step, structured reasoning in large language models and human preferences. We introduce the Alignment Score, a semantic-level metric that compares a model-produced chain of thought traces with a human-pre…

• Audio-DeepThinker: Progressive Reasoning-Aware Reinforcement Learning for High-Quality Chain-of-Thought Emergence in Audio Language Models

  Xiang He, Chenxing Li, Jinting Wang, Yan Rong, Tianxin Xie, Wenfu Wang, Li Liu, Dong Yu · 21 de abril de 2026 · Speech Recognition and Synthesis

  Large Audio-Language Models (LALMs) have made significant progress in audio understanding, yet they primarily operate as perception-and-answer systems without explicit reasoning processes. Existing methods for enhancing audio reasoning rely either on supervised chain-of-thought (CoT) fine-tuning, wh…

• Beyond Fine-Tuning: In-Context Learning and Chain-of-Thought for Reasoned Distractor Generation

  Elaf Alhazmi, Quan Z. Sheng, Wei Emma Zhang · 21 de abril de 2026 · Large Language Models

  Distractor generation (DG) remains a labor-intensive task that still significantly depends on domain experts. The task focuses on generating plausible yet incorrect options, known as distractors, for multiple-choice questions. A reliable distractor must be contextually relevant to the question and a…

• CRISP: Compressing Redundancy in Chain-of-Thought via Intrinsic Saliency Pruning

  Yangsong Lan, Hongliang Dai, Piji Li · 21 de abril de 2026 · Scientific Computing and Data Management

  Long Chain-of-Thought (CoT) reasoning is pivotal for the success of recent reasoning models but suffers from high computational overhead and latency. While prior works attempt to compress CoT via external compressor, they often fail to align with the model's internal reasoning dynamics, resulting in…

• Learning to Correct: Calibrated Reinforcement Learning for Multi-Attempt Chain-of-Thought

  Muhammed Emrullah Ildiz, Halil Alperen Gozeten, Ege Onur Taga, Samet Oymak · 21 de abril de 2026 · Reinforcement Learning in Robotics

  State-of-the-art reasoning models utilize long chain-of-thought (CoT) to solve increasingly complex problems using more test-time computation. In this work, we explore a long CoT setting where the model makes up to K successive attempts at solving a problem, in which each attempt is allowed to build…