Búsqueda: chain of thought

520 artículos encontrados.

• Clustering as Reasoning: A $k$-Means Interpretation of Chain-of-Thought Graph Learning

  Xuanting Xie, Zhaochen Guo, Bingheng Li, Xingtong Yu, Zhifei Liao, Zhao Kang, Yuan Fang · 26 de mayo de 2026 · Advanced Graph Neural Networks

  Chain-of-Thought (CoT) prompting has shown promise in enhancing the reasoning capabilities of large language models (LLMs) on text-attributed graphs (TAGs). This work reframes CoT-based graph learning through the principle of clustering as reasoning, offering a $k$-means interpretation of how iterat…

• PointLLM-R: Enhancing 3D Point Cloud Reasoning via Chain-of-Thought

  Chaoqi Chen, Qile Xu, Wenjun Zhou, Hui Huang · 22 de mayo de 2026 · 3D Shape Modeling and Analysis

  Understanding 3D point clouds through language remains a fundamental challenge in computer graphics and visual computing, due to the irregular structure of point cloud data and the lack of explicit reasoning in existing 3D multimodal models. While Chain-of-Thought (CoT) reasoning has shown strong ef…

• EvalMORAAL: Interpretable Chain-of-Thought and LLM-as-Judge Evaluation for Moral Alignment in Large Language Models

  Hadi Mohammadi, Anastasia Giachanou, Robert A. Bagheri · 22 de mayo de 2026 · Psychology of Moral and Emotional Judgment

  We present EvalMORAAL, a transparent chain-of-thought (CoT) framework that uses two scoring methods (log-probabilities and direct ratings) plus a model-as-judge peer review to evaluate moral alignment in 20 large language models. We assess models on the World Values Survey (55 countries, 19 topics) …

• Mechanics of Bias and Reasoning: Interpreting the Impact of Chain-of-Thought Prompting on Gender Bias in LLMs

  Edie Pearman, Sophia Osborne, Mira Kandlikar-Bloch, Mina Arzaghi, Florian Carichon, Golnoosh Farnadi · 22 de mayo de 2026 · Large Language Models

  Large language models (LLMs) are increasingly deployed in socially sensitive settings despite substantial documentation that they encode gender biases. Chain-of-Thought (CoT) prompting has been proposed as a bias-mitigation approach. However, existing evaluations primarily focus on changes in LLM be…

• Long-Context Reasoning Through Proxy-Based Chain-of-Thought Tuning

  Miao Li, Irina Saparina, Alexander Gurung, Mirella Lapata · 21 de mayo de 2026 · Large Language Models

  Recent large language models support inputs of up to 10 million tokens, yet they perform poorly on long-context tasks that require complex reasoning. Such tasks can be solved using only a subset of the input -- a proxy context -- rather than the full sequence. Despite sharing the same underlying rea…

• On the Cost and Benefit of Chain of Thought: A Learning-Theoretic Perspective

  Yue Zhang, Zhiyi Dong, Tommaso Cesari, Yongyi Mao · 21 de mayo de 2026 · Child and Animal Learning Development

  We develop a learning-theoretic framework for understanding Chain of Thought (CoT). We model CoT as the interaction between an answer map and a chain rule that generates intermediate questions autoregressively, and define the reasoning risk of a hypothesis under this interaction. Our first result is…

• Structured Style-Rewrite with Chain-of-Thought Planning for Low-Resource Character Dialogue

  Chanhui Zhu · 20 de mayo de 2026 · Artificial Intelligence in Games

  Applying Small Language Models (SLMs) to Chinese character-driven generation remains challenging due to data scarcity and the difficulty of disentangling character style. Standard Supervised Fine-Tuning (SFT) often captures surface-level semantics but produces frequent Out-Of-Character (OOC) outputs…

• Passive Construction Site Safety Monitoring via Persona-Scaffolded Adversarial Chain-of-Thought VLM Verification

  Ananth Sriram, Neel Mokaria, Rajveer Singh · 20 de mayo de 2026 · Occupational Health and Safety Research

  Construction remains the deadliest industry sector in the United States, with 1,055 fatal worker injuries recorded in 2023, and the majority preventable. Existing monitoring approaches are expensive, require real-time human operators, or address only a narrow subset of violations. This paper present…

• EgoCoT-Bench: Benchmarking Grounded and Verifiable Operation-Centric Chain of Thought Reasoning for MLLMs

  Yang Dai, Dian Jiao, Tianwei Lin, Wenqiao Zhang · 20 de mayo de 2026 · Multimodal Machine Learning Applications

  The rapid development of Multimodal Large Language Models (MLLMs) has led to growing interest in egocentric video understanding, specifically the ability for MLLMs to recognize fine-grained hand-object interactions, track object state changes over time, and reason about manipulative processes in dyn…

• ACIL: Auto Chain of Thoughts for In-Context Learning

  Rui Chu · 19 de mayo de 2026 · Explainable Artificial Intelligence (XAI)

  Recent advances in large language models (LLMs) have shown that Chain-of-Thought (CoT) reasoning can substantially improve performance on complex reasoning tasks. At the same time, In-Context Learning (ICL) has become an important mechanism for adapting LLMs to new tasks without updating model param…

• Multilingual OCR-Aware Fine-Tuning and Prompt-Guided Chain-of-Thought Reasoning for Multimodal Large Language Models

  Qinwu Xu, Xin Liu, Yifan Jiang, Haoyu Ren · 19 de mayo de 2026 · Multimodal Machine Learning Applications

  Optical character recognition (OCR) and multilingual text understanding remain major failure modes of multimodal large language models (MLLMs), particularly in real-world images containing cluttered layouts, small fonts, blur, occlusion, and complex typography. We present an OCR-aware multilingual…

• The Expressive Power of Low Precision Softmax Transformers with (Summarized) Chain-of-Thought

  Moritz Br\"osamle, Stephan Eckstein · 19 de mayo de 2026 · Evolutionary Algorithms and Applications

  Existing expressivity results for transformers typically rely on hardmax attention, high precision, and other architectural modifications that disconnect them from the models used in practice. We bridge this gap by analyzing standard transformer decoders with softmax attention and rounding of activa…

• The Last Word Often Wins: A Format Confound in Chain-of-Thought Corruption Studies

  Gabriel Garcia · 18 de mayo de 2026 · Large Language Models

  Corruption studies, the standard tool for evaluating chain-of-thought (CoT) faithfulness, infer which steps are ``computationally important'' from accuracy loss when steps are corrupted. We show that when benchmark chains end with an explicit terminal answer line, as in GSM8K and MATH, these tests l…

• COTCAgent: Preventive Consultation via Probabilistic Chain-of-Thought Completion

  Zihan Deng, Xiaozhen Zhong, Chuanzhi Xu · 15 de mayo de 2026 · Machine Learning in Healthcare

  As large language models empower healthcare, intelligent clinical decision support has developed rapidly. Longitudinal electronic health records (EHR) provide essential temporal evidence for accurate clinical diagnosis and analysis. However, current large language models have critical flaws in longi…

• Pause and Reflect: Conformal Aggregation for Chain-of-Thought Reasoning

  Yu Gu, Zijun Yu, Vahid Partovi Nia, Masoud Asgharian · 15 de mayo de 2026 · Mobile Crowdsensing and Crowdsourcing

  Chain-of-thought (CoT) reasoning with self-consistency improves performance by aggregating multiple sampled reasoning paths. In this setting, correctness is no longer tied to a single reasoning trace but to the aggregation rule over a pool of candidate paths, making aggregation uncertainty the centr…

• FireScope: Wildfire Risk Raster Prediction with a Chain-of-Thought Oracle

  Mario Markov (INSAIT, Sofia University "St. Kliment Ohridski"), Stefan Maria Ailuro (INSAIT, Sofia University "St. Kliment Ohridski"), Luc Van Gool (INSAIT, Sofia University "St. Kliment Ohridski"), Konrad Schindler (ETH Zurich), Danda Pani Paudel (INSAIT, Sofia University "St. Kliment Ohridski") · 14 de mayo de 2026 · Data Visualization and Analytics

  Predicting wildfire risk is a reasoning-intensive spatial problem that requires the integration of visual, climatic, and geographic factors to infer continuous risk maps. Existing methods lack the causal reasoning and multimodal understanding required for reliable generalization. We introduce FireSc…

• An Agentic AI Framework with Large Language Models and Chain-of-Thought for UAV-Assisted Logistics Scheduling with Mobile Edge Computing

  Hanwen Zhang, Dusit Niyato, Wei Zhang, Xin Lou, Malcolm Yoke Hean Low · 14 de mayo de 2026 · UAV Applications and Optimization

  In cloud manufacturing, unmanned aerial vehicles (UAVs) can support both product collection and mobile edge computing (MEC). This joint operation forms a hybrid scheduling problem, where physical logistics decisions are coupled with computational task scheduling. In this paper, UAVs collect finished…

• Latent Chain-of-Thought Improves Structured-Data Transformers

  Carson Dudley, Samet Oymak · 13 de mayo de 2026 · Large Language Models

  Chain-of-thought and more broadly test-time compute are known to augment the expressive capabilities of language models and have led to major innovations in reasoning. Motivated by this success, this paper explores latent chain-of-thought as well as the impact of depth and looping for time-series an…

• Drop the Act: Probe-Filtered RL for Faithful Chain-of-Thought Reasoning

  Swapnil Parekh · 13 de mayo de 2026 · Reinforcement Learning in Robotics

  Reasoning models post-hoc rationalize answers they have already committed to internally, producing chains of *reasoning theater*: deliberative-looking steps that contribute nothing to correctness. This wastes inference tokens, pollutes interpretability, and obscures what the model actually computed.…

• When Reasoning Traces Become Performative: Step-Level Evidence that Chain-of-Thought Is an Imperfect Oversight Channel

  Wenkai Li, Fan Yang, Ananya Hazarika, Shaunak A. Mehta, Koichi Onoue · 13 de mayo de 2026 · Large Language Models

  Chain-of-thought (CoT) traces are increasingly used both to improve language model capability and to audit model behavior, implicitly assuming that the visible trace remains synchronized with the computation that determines the answer. We test this assumption with a step-level Detect-Classify-Compar…

• C-CoT: Counterfactual Chain-of-Thought with Vision-Language Models for Safe Autonomous Driving

  Kefei Tian, Yuansheng Lian, Kai Yang, Xiangdong Chen, Shen Li · 12 de mayo de 2026 · Autonomous Vehicle Technology and Safety

  Safety-critical planning in complex environments, particularly at urban intersections, remains a fundamental challenge for autonomous driving. Existing methods, whether rule-based or data-driven, frequently struggle to capture complex scene semantics, infer potential risks, and make reliable decisio…

• Hidden Error Awareness in Chain-of-Thought Reasoning: The Signal Is Diagnostic, Not Causal

  Aojie Yuan, Zhiyuan Julian Su, Haiyue Zhang, Yi Nian, Yue Zhao · 12 de mayo de 2026 · Embodied and Extended Cognition

  Chain-of-thought (CoT) prompting assumes that generated reasoning reflects a model's internal computation. We show this assumption is wrong in a specific, measurable way: models internally detect their own reasoning errors but outwardly express confidence in them. A linear probe on hidden states pre…

• Separate First, Fuse Later: Mitigating Cross-Modal Interference in Audio-Visual LLMs Reasoning with Modality-Specific Chain-of-Thought

  Xuanchen Li, Yuheng Lu, Chenrui Cui, Tianrui Wang, Zikang Huang, Yu Jiang, Long Zhou, Longbiao Wang, Jianwu Dang · 12 de mayo de 2026 · Multimodal Machine Learning Applications

  Audio and vision provide complementary evidence for audio-visual question answering, yet current audio-visual large language models may suffer from cross-modal interference: information from one modality misguides the interpretation of another, thereby inducing hallucinations. We attribute this issu…

• CoEvoT: Co-Evolving Chain-of-Thought Prompting for Graph-LLM Reasoning

  Haohua Niu, Xingtong Yu, Yang Liu, Junfeng Fang, Xuanting Xie, Jie Tan, Zhongjian Zhang, Hong Cheng, Yuan Fang · 11 de mayo de 2026 · Advanced Graph Neural Networks

  Graph learning under distribution shift presents a persistent challenge, where models adapt to new graphs with limited or even no supervision. Recent graph--LLM approaches move toward label-efficient prediction by linearizing graphs into prompts and using large language models (LLMs) as predictors, …

• RCoT-Seg: Reinforced Chain-of-Thought for Video Reasoning and Segmentation

  Junwei Wen, Deshui Miao, Guangming Lu, Xin Li, Wenjie Pei · 11 de mayo de 2026 · Visual Attention and Saliency Detection

  Video Reasoning Segmentation (VRS) aims to segment target objects in videos based on implicit instructions that convey human intent and temporal logic. Existing MLLM-based methods predict masks with a [SEG] token after selecting frames via simple sampling or an auxiliary MLLM, where limited supervis…