Búsqueda: chain of thought

520 artículos encontrados.

• SCIT: Testing Causal Cache Carriers in Latent Chain-of-Thought Models

  Yi Ding, Lijun Huang, Menglin Yang · 28 de agosto de 2026 · Large Language Models

  Latent chain-of-thought models move intermediate reasoning from emitted text into continuous states, improving compactness but hiding the causal object. We introduce SCIT, the Suffix Cache Interchange Test, a causal protocol that constructs exact source-recipient counterfactuals, patches declared ca…

• Improving LLM Interpretability with User-Centric Chain-of-Thought Reasoning

  Philipp Schr\"oppel · 28 de agosto de 2026 · Semantic Web and Ontologies

  Advancing reasoning capabilities allow large language models (LLMs) to tackle increasingly complex problems, while reasoning traces - intermediate steps toward solutions - open up high-stakes applications by enabling human inspection of AI decision-making. However, current approaches prioritize mode…

• Memory Augmentation Unlocks Efficient Chain-of-Thought Reasoning

  Simeng Zhang, Yilong Chen, Wenyuan Zhang, Zhenyu Zhang, Yao Chen, Junyuan Shang, Tingwen Liu · 27 de agosto de 2026 · Multimodal Machine Learning Applications

  Large language models often rely on Chain-of-Thought (CoT) reasoning to solve complex tasks, but verbose reasoning traces introduce substantial inference overhead. CoT compression shortens generation, yet aggressive compression may disrupt logical coherence and degrade performance. We formalize this…

• PA-CoT: Profile-Adaptive Chain-of-Thought for Personalized Nutritional Consulting

  Evgenii Garmashov, Nikita Kulin, Artur Khairullin, Viktor Zhuravlev, Daniil Sukhorukov, Mikhail Mozikov, Ilya Makarov, Sergey Muravyov · 27 de agosto de 2026 · Large Language Models

  In health and nutrition consulting, widely used prompting methods pass the user profile as an unstructured block without a dedicated analysis step, leaving personalization as a critical structural gap. We introduce PA-CoT (Profile-Adaptive Chain-of-Thought), a multi-stage prompting method that treat…

• Right Diagnoses, Decorative Reasoning:A Perturbation Audit of Medical Chain-of-Thought

  Mengzhu Xu, Jifan Gao, Xia Jiang, Yaoxin Wu, Xi Long · 26 de agosto de 2026 · Clinical Reasoning and Diagnostic Skills

  Clinicians read chain-of-thought (CoT) rationales as evidence of medical reasoning, but whether the visible chain plays that role is rarely tested. General-domain CoT-faithfulness probes ignore clinical cost, and medical LLM evaluations treat the chain as a black box. We close this gap with a medica…

• VIG: Visual Information Gain as a Reward Signal for Multimodal Chain-of-Thought Compression

  Wen Luo, Xiaohan Yi, Xiaotao Huang, Liqun Huang · 25 de agosto de 2026 · Multimodal Machine Learning Applications

  Multimodal large reasoning models often rely on long Chain-of-Thought (CoT) traces in which a substantial fraction of tokens, such as repeated visual descriptions, self-reflection, and other visually-disengaged filler, inflate inference cost without contributing to the answer. Existing CoT compressi…

• Mechanistic Interpretability of Chain-of-Thought Reasoning via Sequential Activation Patching

  Murat Dura, Serkan \"Ozt\"urk, Selma Tekir · 25 de agosto de 2026 · Large Language Models

  Large Language Models (LLMs) demonstrate remarkable problem-solving capabilities when guided by Chain-of-Thought (CoT) prompting, yet the internal mechanisms underlying these improvements remain poorly understood. In this work, we investigate where CoT-related causal effects emerge across the genera…

• ChainPrune: Evaluating and Reducing Redundancy in Long Chain-of-Thought Reasoning

  Weihang Pan, Zhengxu Yu, Yuxiang Zhang, Wenzhi Li, Zhongming Jin, Binbin Lin, Xiaofei He, Jieping Ye · 25 de agosto de 2026 · Semantic Web and Ontologies

  Chain-of-Thought (CoT) reasoning has significantly enhanced the multi-step problem-solving capabilities of large language models (LLMs) by introducing explicit intermediate reasoning. However, advanced Large Reasoning Models (LRMs) often exhibit overthinking behaviors, including excessively long rea…

• SAEM: Stage-Aware Expert Management for Memory-Efficient MoE Inference in Chain-of-Thought Reasoning

  Yujie Zhang, Bin Gao, Tulika Mitra · 25 de agosto de 2026 · Parallel Computing and Optimization Techniques

  Chain-of-thought (CoT) prompting improves LLM reasoning by decomposing complex problems into intermediate steps, but its sequential nature increases decoding latency and memory usage. Mixture-of-Experts (MoE) models scale capacity through sparse expert activation, yet their full expert weights often…

• Chain-of-Thought Shows the Path to a Tree: Realizing Branching Complexity

  Debanjan Dutta, Anish Chakrabarty, Swagatam Das · 13 de agosto de 2026 · Scientific Research and Philosophical Inquiry

  Chain of Thought (CoT) lifts the expressive ceiling of bounded-depth Transformers, with characterizations tying the number of CoT steps to circuit complexity classes. What remains largely missing are concrete instantiations with explicit, depth-bounded constructions, and the traversal procedures suc…

• SCOUT: Unlocking Enhanced Spatial Reasoning via Structured Chain-of-Thought and Multi-Objective Process Reward

  Zile Zhou, Huining Yuan, Weichen Zhang, Xinlei Chen, Xiao-ping Zhang · 13 de agosto de 2026 · Multimodal Machine Learning Applications

  Existing Vision-Language Models (VLMs) exhibits a critical bottleneck in robust spatial reasoning. Recent reinforcement learning (RL) methods aim to close this gap with verifiable outcomes, yet they suffer from poor credit assignment across intermediate reasoning steps. Concurrently, structured reas…

• Social Chain of Thought: A Multi-Agent Architecture Grounded in Medical Differential Diagnosis Methodology

  Del Coburn, Scott Sanner, Dan Silver · 13 de agosto de 2026 · Clinical Reasoning and Diagnostic Skills

  Medical diagnostic reasoning is a high-impact use case for LLMs that carries significant implications for the health and wellbeing of users. When OpenAI (2026) reports that more than 5% of ChatGPT messages globally are healthcare-related, the transparency of these systems becomes a serious design co…

• FaithformBench: Benchmarking Faithfulness of Mathematical Chain-of-Thought Autoformalisation

  Rob Cornish, Iacopo Ghinassi, Po-Hung Yeh, Shuqi Liu, Qiyuan Xu, Haoxuan Yin, Dominik Wagner, Wenda Li, Yee Whye Teh, Luke Ong · 12 de agosto de 2026 · Model-Driven Software Engineering Techniques

  Autoformalisation (AF) systems map natural language reasoning steps into formal statements in a proof assistant such as Lean. We consider how to assess the faithfulness of these systems. Existing approaches require expensive human-annotated ground truth, or rely on LLM judges or embedding models, wh…

• When Chain-of-Thought Helps and When It Hurts: An Empirical Investigation of the Serial-Depth Bottleneck in LLM Reasoning

  Tughanbulut Kurtulush · 12 de agosto de 2026 · Large Language Models

  It is widely assumed that chain-of-thought (CoT) prompting universally improves LLM reasoning. We investigate this through the conceptual framework of the H_dp bandwidth bound (Chen et al., 2024): although the formal bound binds only asymptotically (at astronomically large prompt lengths), it identi…

• MathShikkha: A Controlled Study of Answer-Only and Chain-of-Thought Supervision for Bangla Mathematical Reasoning in Small Language Models

  Rahma Simin Ali, Jawad Hossain · 11 de agosto de 2026 · Large Language Models

  Mathematical reasoning remains challenging in low-resource languages such as Bangla. We study whether teacher-generated Bangla Chain-of-Thought (CoT) supervision provides benefits beyond ordinary supervised fine-tuning. We construct \textsc{MathShikkha}, a Bangla mathematical reasoning dataset with …

• Mean-Field Dynamics of Chain-of-Thought Reasoning in Large Language Models

  Hao Ai · 7 de agosto de 2026 · Semantic Web and Ontologies

  Large language models (LLMs) with chain-of-thought reasoning have been widely applied in recent years, and theoretical explanations of their behavior may help deepen our understanding and guide model optimization. In this study, we introduce a framework that seeks statistical regularities and theore…

• ODRA: Synthesizing Cognitive Behavioral Therapy Sessions with Structured Chain-Of-Thought and Dynamic Patient Resistance

  Javier Rodriguez-Juan, Hiba Arnaout, Jose Garcia-Rodriguez, David Tom\'as, Iryna Gurevych · 6 de agosto de 2026 · Digital Mental Health Interventions

  Synthetic generation of Cognitive Behavioral Therapy (CBT) sessions is challenged by two competing demands: adhering to strict therapeutic structure while modeling the resistant, unpredictable behavior of real patients. Existing script-based methods fail to capture dynamic therapeutic interactions, …

• Chain-of-Thought Monitoring Can Be Unreliable in Implicit-Influence Settings

  Agatha Duzan, Asa Cooper Stickland · 6 de agosto de 2026 · Mental Health Research Topics

  Chain-of-thought (CoT) monitoring is increasingly treated as an important safety layer for frontier reasoning models. Most monitorability evaluations study explicit-influence settings: setups where the prompt directly incentivizes the model to hide something, e.g., by instructing it to perform a hid…

• Evading Chain-of-Thought Monitoring Through Model Poisoning

  Giorgio Severi, Shujaat Mirza, Blake Bullwinkel, Amanda Minnich · 5 de agosto de 2026 · Adversarial Robustness in Machine Learning

  Chain-of-thought (CoT) monitoring is an increasingly important component of AI safety stacks but relies on the assumption that a model's reasoning trace is informative about its actions. This work studies the limits of CoT monitoring through the lens of model poisoning. We demonstrate that backdoors…

• The Tell-Tale Trace: Detecting Reasoning Failures in LLMs Using Chain-of-Thought Dynamics

  Shashwat Sourav, Aishwarya Balwani · 5 de agosto de 2026 · Semantic Web and Ontologies

  Chain-of-thought (CoT) reasoning improves large language model (LLM) performance while also providing an observable interface to the model's reasoning process. Existing approaches that leverage verbalized CoTs to monitor reasoning correctness, however, largely evaluate the semantic correctness or co…

• A False Average: Chain-of-Thought Monitors Collapse Where They Are the Only Defense

  Shikhar Shiromani, Leo Richter · 4 de agosto de 2026 · Security and Verification in Computing

  Chain-of-thought (CoT) monitoring is meant to catch the reward hacks that look clean in the actions and betray themselves only in the reasoning. We show that this is exactly where an adversary who controls the reasoning can defeat it. Rewriting only an agent's reasoning to read as good-faith enginee…

• Native Multilingual Chain-of-Thought Reasoning in Low-Resource Southeast Asian Languages

  Sean Gip Lim, William Chandra Tjhi, Hai Leong Chieu · 4 de agosto de 2026 · Natural Language Processing Techniques

  Large Language Models have achieved substantial progress in reasoning capabilities. Yet in low-resource native settings, many suffer from cross-lingual collapse, reverting to English during intermediate steps that require complex logical reasoning. This presents a cold-start bottleneck for policy op…

• On the Generalization of Steering Vectors for Chain-of-Thought Faithfulness

  Matthew Nguyen, Kyle Cox, Austin Meek, Iv\'an Arcuschin · 3 de agosto de 2026 · Large Language Models

  Model capabilities have improved in large part due to scaling chain of thought. This has been a promising development for AI safety--where models verbalize their reasoning, it is possible to monitor it. However, in some cases, models do not verbalize important steps in their reasoning process. For e…

• How Hard Does It Think? Analyzing Step-Aware Reasoning Energy in LLM Chain-of-Thought Trajectories

  Hui Wei, Junda Wu, Sheldon Yu, Sizhe Zhou, Yizhu Jiao, Ming Zhong, Bowen Jin, Tong Yu, Shijia Pan, Jiawei Han, Julian McAuley · 3 de agosto de 2026 · Semantic Web and Ontologies

  Understanding how computational effort is allocated across individual chain-of-thought (CoT) reasoning steps remains an open challenge: existing interpretability methods rely on output-level signals or collapse processing depth into a single trajectory-level scalar, leaving step-wise effort opaque. …

• Demystifying Entropy-based Selection for Chain-of-Thought Compression in Large Reasoning Models

  Sara Candussio, Daniel Scalena, Luca Bortolussi, Elisabetta Fersini, Malvina Nissim, Gabriele Sarti · 31 de julio de 2026 · Constraint Satisfaction and Optimization

  Entropy-based pruning has been proposed as an effective method for compressing Chain-of-Thought (CoT) reasoning with negligible accuracy loss. We test the robustness of low- and high-entropy CoT step selection methods across various models and reasoning tasks, showing that entropy offers no advantag…