Búsqueda: chain of thought

524 artículos encontrados.

• Think Consistently, Reason Efficiently: Energy-Based Calibration for Implicit Chain-of-Thought

  Zhikang Chen, Sen Cui, Deheng Ye, Yu Zhang, Yatao Bian, Tingting Zhu · 11 de noviembre de 2025 · Multimodal Machine Learning Applications

  Large Language Models (LLMs) have demonstrated strong reasoning capabilities through \emph{Chain-of-Thought} (CoT) prompting, which enables step-by-step intermediate reasoning. However, explicit CoT methods rely on discrete token-level reasoning processes that are prone to error propagation and limi…

• Optimizing Chain-of-Thought Confidence via Topological and Dirichlet Risk Analysis

  Abhishek More, Anthony Zhang, Nicole Bonilla, Ashvik Vivekan, Kevin Zhu, Parham Sharafoleslami, Maheep Chaudhary · 11 de noviembre de 2025 · Advanced Graph Neural Networks

  Chain-of-thought (CoT) prompting enables Large Language Models to solve complex problems, but deploying these models safely requires reliable confidence estimates, a capability where existing methods suffer from poor calibration and severe overconfidence on incorrect predictions. We propose Enhanced…

• Transformers Provably Learn Chain-of-Thought Reasoning with Length Generalization

  Yu Huang, Zixin Wen, Aarti Singh, Yuejie Chi, Yuxin Chen · 11 de noviembre de 2025 · Multimodal Machine Learning Applications

  The ability to reason lies at the core of artificial intelligence (AI), and challenging problems usually call for deeper and longer reasoning to tackle. A crucial question about AI reasoning is whether models can extrapolate learned reasoning patterns to solve harder tasks with longer chain-of-thoug…

• MONICA: Real-Time Monitoring and Calibration of Chain-of-Thought Sycophancy in Large Reasoning Models

  Jingyu Hu, Shu Yang, Xilin Gong, Hongming Wang, Weiru Liu, Di Wang · 11 de noviembre de 2025 · Explainable Artificial Intelligence (XAI)

  Large Reasoning Models (LRMs) suffer from sycophantic behavior, where models tend to agree with users' incorrect beliefs and follow misinformation rather than maintain independent reasoning. This behavior undermines model reliability and poses societal risks. Mitigating LRM sycophancy requires monit…

• Effectiveness of Chain-of-Thought in Distilling Reasoning Capability from Large Language Models

  Cong-Thanh Do, Rama Doddipatla, Kate Knill · 10 de noviembre de 2025 · Large Language Models

  Chain-of-Thought (CoT) prompting is a widely used method to improve the reasoning capability of Large Language Models (LLMs). More recently, CoT has been leveraged in Knowledge Distillation (KD) to transfer reasoning capability from a larger LLM to a smaller one. This paper examines the role of CoT …

• VeriCoT: Neuro-symbolic Chain-of-Thought Validation via Logical Consistency Checks

  Yu Feng, Nathaniel Weir, Kaj Bostrom, Sam Bayless, Darion Cassel, Sapana Chaudhary, Benjamin Kiesl-Reiter, Huzefa Rangwala · 7 de noviembre de 2025 · Explainable Artificial Intelligence (XAI)

  LLMs can perform multi-step reasoning through Chain-of-Thought (CoT), but they cannot reliably verify their own logic. Even when they reach correct answers, the underlying reasoning may be flawed, undermining trust in high-stakes scenarios. To mitigate this issue, we introduce VeriCoT, a neuro-symbo…

• Logit-Entropy Adaptive Stopping Heuristic for Efficient Chain-of-Thought Reasoning

  Mohammad Atif Quamar, Mohammad Areeb · 7 de noviembre de 2025 · Large Language Models

  Chain-of-Thought (CoT) prompting is a key technique for enabling complex reasoning in large language models. However, generating full, fixed-length rationales is computationally wasteful, inflating both token usage and latency. We introduce LEASH: Logit-Entropy Adaptive Stopping Heuristic, a trainin…

• CoTox: Chain-of-Thought-Based Molecular Toxicity Reasoning and Prediction

  Jueon Park, Yein Park, Minju Song, Soyon Park, Donghyeon Lee, Seungheun Baek, Jaewoo Kang · 6 de noviembre de 2025 · Computational Drug Discovery Methods

  Drug toxicity remains a major challenge in pharmaceutical development. Recent machine learning models have improved in silico toxicity prediction, but their reliance on annotated data and lack of interpretability limit their applicability. This limits their ability to capture organ-specific toxiciti…

• Re-FORC: Adaptive Reward Prediction for Efficient Chain-of-Thought Reasoning

  Renos Zabounidis, Aditya Golatkar, Michael Kleinman, Alessandro Achille, Wei Xia, Stefano Soatto · 5 de noviembre de 2025 · Reinforcement Learning in Robotics

  We propose Re-FORC, an adaptive reward prediction method that, given a context, enables prediction of the expected future rewards as a function of the number of future thinking tokens. Re-FORC trains a lightweight adapter on reasoning models, demonstrating improved prediction with longer reasoning a…

• Curriculum Design for Trajectory-Constrained Agent: Compressing Chain-of-Thought Tokens in LLMs

  Georgios Tzannetos, Parameswaran Kamalaruban, Adish Singla · 5 de noviembre de 2025 · Reinforcement Learning in Robotics

  Training agents to operate under strict constraints during deployment, such as limited resource budgets or stringent safety requirements, presents significant challenges, especially when these constraints render the task complex. In this work, we propose a curriculum learning strategy that gradually…

• When Visualizing is the First Step to Reasoning: MIRA, a Benchmark for Visual Chain-of-Thought

  Yiyang Zhou, Haoqin Tu, Zijun Wang, Zeyu Wang, Niklas Muennighoff, Fan Nie, Yejin Choi, James Zou, Chaorui Deng, Shen Yan, Haoqi Fan, Cihang Xie, Huaxiu Yao, Qinghao Ye · 5 de noviembre de 2025 · Multimodal Machine Learning Applications

  We propose MIRA, a new benchmark designed to evaluate models in scenarios where generating intermediate visual images is essential for successful reasoning. Unlike traditional CoT methods that rely solely on text, tasks in MIRA require models to generate and utilize intermediate images - such as ske…

• Scaling Graph Chain-of-Thought Reasoning: A Multi-Agent Framework with Efficient LLM Serving

  Chengying Huan, Ziheng Meng, Yongchao Liu, Zhengyi Yang, Yun Zhu, Yue Yun, Shipeng Li, Rong Gu, Xiabao Wu, Haitao Zhang, Chuntao Hong, Shaonan Ma, Guihai Chen, Chen Tian · 4 de noviembre de 2025 · Advanced Graph Neural Networks

  Graph Chain-of-Thought (Graph-CoT) enables large language models (LLMs) to perform step-by-step reasoning over graph-structured knowledge, but existing pipelines suffer from low accuracy, excessive token usage, high latency, and low throughput due to single-agent monolithic prompts, repeated context…

• Analyzing the Power of Chain of Thought through Memorization Capabilities

  Lijia Yu, Xiao-Shan Gao, Lijun Zhang · 4 de noviembre de 2025 · Large Language Models

  It has been shown that the chain of thought (CoT) can enhance the power of large language models (LLMs) to solve certain mathematical reasoning problems. However, the capacity of CoT is still not fully explored. As an important instance, the following basic question has not yet been answered: Does C…

• Inference-Time Chain-of-Thought Pruning with Latent Informativeness Signals

  Sophie Li (Columbia University), Nicholas Huang (University of British Columbia), Nayan Saxena (Algoverse AI Research), Nina Luo (Harvey Mudd College), Vincent Lin (University of Florida), Kevin Zhu (Algoverse AI Research), Sunishchal Dev (Algoverse AI Research) · 4 de noviembre de 2025 · Large Language Models

  Large language models (LLMs) improve reasoning accuracy when generating multiple candidate solutions at test time, but standard methods like Best-of-N (BoN) incur high computational cost by fully generating all branches. Self-Truncation Best-of-N (ST-BoN) mitigates this by truncating unpromising pat…

• Inverse Knowledge Search over Verifiable Reasoning: Synthesizing a Scientific Encyclopedia from a Long Chains-of-Thought Knowledge Base

  Yu Li, Yuan Huang, Tao Wang, Caiyu Fan, Xiansheng Cai, Sihan Hu, Xinzijian Liu, Cheng Shi, Mingjun Xu, Zhen Wang, Yan Wang, Xiangqi Jin, Tianhan Zhang, Linfeng Zhang, Lei Wang, Youjin Deng, Pan Zhang, Weijie Sun, Xingyu Li, Weinan E, Linfeng Zhang, Zhiyuan Yao, Kun Chen · 3 de noviembre de 2025 · Scientific Computing and Data Management

  Most scientific materials compress reasoning, presenting conclusions while omitting the derivational chains that justify them. This compression hinders verification by lacking explicit, step-wise justifications and inhibits cross-domain links by collapsing the very pathways that establish the logica…

• Measuring Chain-of-Thought Monitorability Through Faithfulness and Verbosity

  Austin Meek, Eitan Sprejer, Iv\'an Arcuschin, Austin J. Brockmeier, Steven Basart · 3 de noviembre de 2025 · Personal Information Management and User Behavior

  Chain-of-thought (CoT) outputs let us read a model's step-by-step reasoning. Since any long, serial reasoning process must pass through this textual trace, the quality of the CoT is a direct window into what the model is thinking. This visibility could help us spot unsafe or misaligned behavior (mon…

• Reasoning Models Sometimes Output Illegible Chains of Thought

  Arun Jose · 3 de noviembre de 2025 · Large Language Models

  Language models trained via outcome-based reinforcement learning (RL) to reason using chain-of-thought (CoT) have shown remarkable performance. Monitoring such a model's CoT may allow us to understand its intentions and detect potential malicious behavior. However, to be effective, this requires tha…

• VCORE: Variance-Controlled Optimization-based Reweighting for Chain-of-Thought Supervision

  Xuan Gong, Senmiao Wang, Hanbo Huang, Ruoyu Sun, Shiyu Liang · 3 de noviembre de 2025 · Large Language Models

  Supervised fine-tuning (SFT) on long chain-of-thought (CoT) trajectories has emerged as a crucial technique for enhancing the reasoning abilities of large language models (LLMs). However, the standard cross-entropy loss treats all tokens equally, ignoring their heterogeneous contributions across a r…

• ThinkMorph: Emergent Properties in Multimodal Interleaved Chain-of-Thought Reasoning

  Jiawei Gu, Yunzhuo Hao, Huichen Will Wang, Linjie Li, Michael Qizhe Shieh, Yejin Choi, Ranjay Krishna, Yu Cheng · 31 de octubre de 2025 · Multimodal Machine Learning Applications

  Multimodal reasoning requires iterative coordination between language and vision, yet it remains unclear what constitutes a meaningful interleaved chain of thought. We posit that text and image thoughts should function as complementary rather than isomorphic modalities that mutually advance reasonin…

• The Kinetics of Reasoning: How Chain-of-Thought Shapes Learning in Transformers?

  Zihan Pengmei, Costas Mavromatis, Zhengyuan Shen, Yunyi Zhang, Vassilis N. Ioannidis, Huzefa Rangwala · 31 de octubre de 2025 · Cognitive Science and Education Research

  Chain-of-thought (CoT) supervision can substantially improve transformer performance, yet the mechanisms by which models learn to follow and benefit from CoT remain poorly understood. We investigate these learning dynamics through the lens of grokking by pretraining transformers on symbolic reasonin…

• StreamingCoT: A Dataset for Temporal Dynamics and Multimodal Chain-of-Thought Reasoning in Streaming VideoQA

  Yuhang Hu, Zhenyu Yang, Shihan Wang, Shengsheng Qian, Bin Wen, Fan Yang, Tingting Gao, Changsheng Xu · 30 de octubre de 2025 · Video Analysis and Summarization

  The rapid growth of streaming video applications demands multimodal models with enhanced capabilities for temporal dynamics understanding and complex reasoning. However, current Video Question Answering (VideoQA) datasets suffer from two critical limitations: 1) Static annotation mechanisms fail to …

• SemCoT: Accelerating Chain-of-Thought Reasoning through Semantically-Aligned Implicit Tokens

  Yinhan He, Wendy Zheng, Yaochen Zhu, Zaiyi Zheng, Lin Su, Sriram Vasudevan, Qi Guo, Liangjie Hong, Jundong Li · 30 de octubre de 2025 · Semantic Web and Ontologies

  The verbosity of Chain-of-Thought (CoT) reasoning hinders its mass deployment in efficiency-critical applications. Recently, implicit CoT approaches have emerged, which encode reasoning steps within LLM's hidden embeddings (termed ``implicit reasoning'') rather than explicit tokens. This approach ac…

• Can Aha Moments Be Fake? Identifying True and Decorative Thinking Steps in Chain-of-Thought

  Jiachen Zhao, Yiyou Sun, Weiyan Shi, Dawn Song · 30 de octubre de 2025 · Large Language Models

  Recent large language models (LLMs) can generate long Chain-of-Thought (CoT) at test time, enabling them to solve complex tasks. These reasoning steps in CoT are often assumed as a faithful reflection of the model's internal thinking process, and used to monitor unsafe intentions. However, we find m…

• Latent Chain-of-Thought for Visual Reasoning

  Guohao Sun, Hang Hua, Jian Wang, Jiebo Luo, Sohail Dianat, Majid Rabbani, Raghuveer Rao, Zhiqiang Tao · 29 de octubre de 2025 · Multimodal Machine Learning Applications

  Chain-of-thought (CoT) reasoning is critical for improving the interpretability and reliability of Large Vision-Language Models (LVLMs). However, existing training algorithms such as SFT, PPO, and GRPO may not generalize well across unseen reasoning tasks and heavily rely on a biased reward model. T…

• A Pragmatic Way to Measure Chain-of-Thought Monitorability

  Scott Emmons, Roland S. Zimmermann, David K. Elson, Rohin Shah · 29 de octubre de 2025 · Large Language Models

  While Chain-of-Thought (CoT) monitoring offers a unique opportunity for AI safety, this opportunity could be lost through shifts in training practices or model architecture. To help preserve monitorability, we propose a pragmatic way to measure two components of it: legibility (whether the reasoning…