Búsqueda: chain of thought

520 artículos encontrados.

• Cognitive Chain-of-Thought (CoCoT): Structured Multimodal Reasoning about Social Situations

  Eunkyu Park, Wesley Hanwen Deng, Gunhee Kim, Motahhare Eslami, Maarten Sap · 21 de abril de 2026 · Multimodal Machine Learning Applications

  Chain-of-Thought (CoT) prompting helps models think step by step. But naive CoT breaks down in visually grounded social tasks, where models must perceive, understand, and judge all at once; bridging perception with norm-grounded reasoning. Recent work has introduced structured reasoning for multi-tu…

• Chain-of-Thought Degrades Visual Spatial Reasoning Capabilities of Multimodal LLMs

  Sai Srinivas Kancheti, Aditya Sanjiv Kanade, Vineeth N. Balasubramanian, Tanuja Ganu · 20 de abril de 2026 · Multimodal Machine Learning Applications

  Multimodal Reasoning Models (MRMs) leveraging Chain-of-Thought (CoT) based thinking have revolutionized mathematical and logical problem-solving. However, we show that this paradigm struggles with generalized spatial intelligence. We perform a comprehensive evaluation of seventeen models across thir…

• Analyzing Chain of Thought (CoT) Approaches in Control Flow Code Deobfuscation Tasks

  Seyedreza Mohseni, Sarvesh Baskar, Edward Raff, Manas Gaur · 20 de abril de 2026 · Software Engineering Research

  Code deobfuscation is the task of recovering a readable version of a program while preserving its original behavior. In practice, this often requires days or even months of manual work with complex and expensive analysis tools. In this paper, we explore an alternative approach based on Chain-of-Thou…

• LLM Reasoning Is Latent, Not the Chain of Thought

  Wenshuo Wang · 20 de abril de 2026 · Neurobiology of Language and Bilingualism

  This position paper argues that large language model (LLM) reasoning should be studied as latent-state trajectory formation rather than as faithful surface chain-of-thought (CoT). This matters because claims about faithfulness, interpretability, reasoning benchmarks, and inference-time intervention …

• Mamba-SSM with LLM Reasoning for Biomarker Discovery: Causal Feature Refinement via Chain-of-Thought Gene Evaluation

  Pushpa Kumar Balan, Aijing Feng · 17 de abril de 2026 · Bioinformatics and Genomic Networks

  Gradient saliency from deep sequence models surfaces candidate biomarkers efficiently, but the resulting gene lists are contaminated by tissue-composition confounders that degrade downstream classifiers. We study whether LLM chain-of-thought (CoT) reasoning can faithfully filter these confounders, a…

• CoTEvol: Self-Evolving Chain-of-Thoughts for Data Synthesis in Mathematical Reasoning

  Zhuo Wang, Zhuo Zhang, Yafu Li, Yu Cheng, Lizhen Qu, Zenglin Xu · 17 de abril de 2026 · Machine Learning in Materials Science

  Large Language Models (LLMs) exhibit strong mathematical reasoning when trained on high-quality Chain-of-Thought (CoT) that articulates intermediate steps, yet costly CoT curation hinders further progress. While existing remedies such as distillation from stronger LLMs and self-synthesis based on te…

• Correct Prediction, Wrong Steps? Consensus Reasoning Knowledge Graph for Robust Chain-of-Thought Synthesis

  Zipeng Ling, Shuliang Liu, Shenghong Fu, Yuehao Tang, Seonil Son, Yao Wan, Xuming Hu · 16 de abril de 2026 · Advanced Graph Neural Networks

  LLM reasoning traces suffer from complex flaws -- *Step Internal Flaws* (logical errors, hallucinations, etc.) and *Step-wise Flaws* (overthinking, underthinking), which vary by sample. A natural approach would be to provide ground-truth labels to guide LLMs' reasoning. Contrary to intuition, we sho…

• Pruning Long Chain-of-Thought of Large Reasoning Models via Small-Scale Preference Optimization

  Bin Hong, Jiayu Liu, Kai Zhang, Jianwen Sun, Mengdi Zhang, Zhenya Huang · 16 de abril de 2026 · Large Language Models

  Recent advances in Large Reasoning Models (LRMs) have demonstrated strong performance on complex tasks through long Chain-of-Thought (CoT) reasoning. However, their lengthy outputs increase computational costs and may lead to overthinking, raising challenges in balancing reasoning effectiveness and …

• LongCoT: Benchmarking Long-Horizon Chain-of-Thought Reasoning

  Sumeet Ramesh Motwani, Daniel Nichols, Charles London, Peggy Li, Fabio Pizzati, Acer Blake, Hasan Hammoud, Tavish McDonald, Akshat Naik, Alesia Ivanova, Vignesh Baskaran, Ivan Laptev, Ruben Glatt, Tal Ben-Nun, Philip Torr, Natasha Jaques, Ameya Prabhu, Brian Bartoldson, Bhavya Kailkhura, Christian Schroeder de Witt · 16 de abril de 2026 · Machine Learning in Materials Science

  As language models are increasingly deployed for complex autonomous tasks, their ability to reason accurately over longer horizons becomes critical. An essential component of this ability is planning and managing a long, complex chain-of-thought (CoT). We introduce LongCoT, a scalable benchmark of 2…

• Sample Complexity of Autoregressive Reasoning: Chain-of-Thought vs. End-to-End

  Steve Hanneke, Idan Mehalel, Shay Moran · 15 de abril de 2026 · Large Language Models

  Modern large language models generate text autoregressively, producing tokens one at a time. To study the learnability of such systems, Joshi et al. (COLT 2025) introduced a PAC-learning framework for next-token generators, the primitive underlying autoregressive models. In this framework, an unknow…

• AdaMCoT: Rethinking Cross-Lingual Factual Reasoning through Adaptive Multilingual Chain-of-Thought

  Weihua Zheng, Xin Huang, Zhengyuan Liu, Tarun Kumar Vangani, Bowei Zou, Xiyan Tao, Yuhao Wu, Ai Ti Aw, Nancy F. Chen, Roy Ka-Wei Lee · 15 de abril de 2026 · Large Language Models

  Large language models (LLMs) have shown impressive multilingual capabilities through pretraining on diverse corpora. Although these models show strong reasoning abilities, their performance varies significantly between languages due to the imbalanced distribution of training data. Existing approache…

• Learning Chain Of Thoughts Prompts for Predicting Entities, Relations, and even Literals on Knowledge Graphs

  Alkid Baci, Luke Friedrichs, Caglar Demir, N'Dah Jean Kouagou, Axel-Cyrille Ngonga Ngomo · 15 de abril de 2026 · Advanced Graph Neural Networks

  Knowledge graph embedding (KGE) models perform well on link prediction but struggle with unseen entities, relations, and especially literals, limiting their use in dynamic, heterogeneous graphs. In contrast, pretrained large language models (LLMs) generalize effectively through prompting. We reformu…

• Measuring and curing reasoning rigidity: from decorative chain-of-thought to genuine faithfulness

  Abhinaba Basu, Pavan Chakraborty · 14 de abril de 2026 · Artificial Intelligence in Healthcare and Education

  Language models increasingly show their work by writing step-by-step reasoning before answering. But are these steps genuinely used, or is the answer rigid - fixed before reasoning begins? We introduce the Step-Level Reasoning Capacity (SLRC) metric and prove it is a consistent causal estimator (The…

• FACT-E: Causality-Inspired Evaluation for Trustworthy Chain-of-Thought Reasoning

  Yuxi Sun, Aoqi Zuo, Haotian Xie, Wei Gao, Mingming Gong, Jing Ma · 14 de abril de 2026 · Explainable Artificial Intelligence (XAI)

  Chain-of-Thought (CoT) prompting has improved LLM reasoning, but models often generate explanations that appear coherent while containing unfaithful intermediate steps. Existing self-evaluation approaches are prone to inherent biases: the model may confidently endorse coherence even when the step-to…

• How does Chain of Thought decompose complex tasks?

  Amrut Nadgir, Vijay Balasubramanian, Pratik Chaudhari · 13 de abril de 2026 · Text Readability and Simplification

  Many language tasks can be modeled as classification problems where a large language model (LLM) is given a prompt and selects one among many possible answers. We show that the classification error in such problems scales as a power law in the number of classes. This has a dramatic consequence: the …

• Revisiting the Capacity Gap in Chain-of-Thought Distillation from a Practical Perspective

  Tokio Kajitsuka, Ukyo Honda, Sho Takase · 13 de abril de 2026 · Mind wandering and attention

  Chain-of-thought (CoT) distillation transfers reasoning behaviors from a strong teacher to a smaller student, but prior work reports a capacity gap: distillation may fail when the teacher-student capability mismatch is large. We revisit the capacity gap from a practical perspective by re-examining c…

• Tool-MCoT: Tool Augmented Multimodal Chain-of-Thought for Content Safety Moderation

  Shutong Zhang, Dylan Zhou, Yinxiao Liu, Yang Yang, Huiwen Luo, Wenfei Zou · 10 de abril de 2026 · Hate Speech and Cyberbullying Detection

  The growth of online platforms and user content requires strong content moderation systems that can handle complex inputs from various media types. While large language models (LLMs) are effective, their high computational cost and latency present significant challenges for scalable deployment. To a…

• State-of-the-Art Arabic Language Modeling with Sparse MoE Fine-Tuning and Chain-of-Thought Distillation

  Navan Preet Singh, Anurag Garikipati, Ahmed Abulkhair, Jyani Akshay Jagdishbhai, Atul Yaduvanshi, Amarendra Chaudhary, Madalina Ciobanu, Qingqing Mao, Ritankar Das · 9 de abril de 2026 · Natural Language Processing Techniques

  This paper introduces Arabic-DeepSeek-R1, an application-driven open-source Arabic LLM that leverages a sparse MoE backbone to address the digital equity gap for under-represented languages, and establishes a new SOTA across the entire Open Arabic LLM Leaderboard (OALL). Our four-phase CoT distillat…

• Graph-Based Chain-of-Thought Pruning for Reducing Redundant Reflections in Reasoning LLMs

  Hongyuan Yuan, Xinran He, Run Shao, Bolei He, Xianwei Xue, Mengke Chen, Qiutong Pan, Haiwei Wang, Haifeng Li · 8 de abril de 2026 · Large Language Models

  Extending CoT through RL has been widely used to enhance the reasoning capabilities of LLMs. However, due to the sparsity of reward signals, it can also induce undesirable thinking patterns such as overthinking, i.e., generating redundant intermediate reasoning content. In this work, we argue that a…

• Learning to Edit Knowledge via Instruction-based Chain-of-Thought Prompting

  Jinhu Fu, Yan Bai, Longzhu He, Yihang Lou, Yanxiao Zhao, Li Sun, Sen Su · 8 de abril de 2026 · Large Language Models

  Large language models (LLMs) can effectively handle outdated information through knowledge editing. However, current approaches face two key limitations: (I) Poor generalization: Most approaches rigidly inject new knowledge without ensuring that the model can use it effectively to solve practical pr…

• The illusion of reasoning: step-level evaluation reveals decorative chain-of-thought in frontier language models

  Abhinaba Basu, Pavan Chakraborty · 8 de abril de 2026 · Artificial Intelligence in Healthcare and Education

  Language models increasingly "show their work" by writing step-by-step reasoning before answering. But are these reasoning steps genuinely used, or decorative narratives generated after the model has already decided? We introduce step-level faithfulness evaluation - removing one reasoning sentence a…

• ETR: Entropy Trend Reward for Efficient Chain-of-Thought Reasoning

  Xuan Xiong, Huan Liu, Li Gu, Zhixiang Chi, Yue Qiu, Yuanhao Yu, Yang Wang · 8 de abril de 2026 · Large Language Models

  Chain-of-thought (CoT) reasoning improves large language model performance on complex tasks, but often produces excessively long and inefficient reasoning traces. Existing methods shorten CoTs using length penalties or global entropy reduction, implicitly assuming that low uncertainty is desirable t…

• Shorter, but Still Trustworthy? An Empirical Study of Chain-of-Thought Compression

  Lingjie Zeng, Xiaofan Chen, Yanbo Wang, Xiuying Chen · 7 de abril de 2026 · Personal Information Management and User Behavior

  Long chain-of-thought (Long-CoT) reasoning models have motivated a growing body of work on compressing reasoning traces to reduce inference cost, yet existing evaluations focus almost exclusively on task accuracy and token savings. Trustworthiness properties, whether acquired or reinforced through p…

• Strengthening Human-Centric Chain-of-Thought Reasoning Integrity in LLMs via a Structured Prompt Framework

  Jiling Zhou, Aisvarya Adeseye, Seppo Virtanen, Antti Hakkala, Jouni Isoaho · 7 de abril de 2026 · Network Security and Intrusion Detection

  Chain-of-Thought (CoT) prompting has been used to enhance the reasoning capability of LLMs. However, its reliability in security-sensitive analytical tasks remains insufficiently examined, particularly under structured human evaluation. Alternative approaches, such as model scaling and fine-tuning c…

• Student-in-the-Loop Chain-of-Thought Distillation via Generation-Time Selection

  Chaoqun He, Yingfa Chen, Chaojun Xiao, Xu Han, Lijie Wen · 6 de abril de 2026 · Intelligent Tutoring Systems and Adaptive Learning

  Large reasoning models achieve strong performance on complex tasks through long chain-of-thought (CoT) trajectories, but directly transferring such reasoning processes to smaller models remains challenging. A key difficulty is that not all teacher-generated reasoning trajectories are suitable for st…