Suche: chain of thought

520 Paper gefunden.

• Retroactive Chain-of-Thought (RetroCoT): Forensic Reconstruction Prompts as a Safety Diagnostic Across Model Generations

  Samira Hajizadeh · 7. Juli 2026 · Large Language Models

  Safety alignment in large language models is typically evaluated against direct, imperative harmful requests. We show that this alignment is highly conditioned on pragmatic register: models that refuse a direct request frequently comply when the same underlying objective is expressed through a diffe…

• Detecting Answer-Driven Reasoning in LLM-Based Educational Tutors via Truncated Chain-of-Thought Auditing

  Bonan Shen, Dingyan Shang, Youting Wang, Tao Ning · 7. Juli 2026 · Intelligent Tutoring Systems and Adaptive Learning

  Large language model (LLM) tutors often produce fluent step-by-step explanations, but a correct and pedagogically formatted response does not guarantee that the answer was derived from the student-facing problem. In realistic tutoring systems, the model may also have access to teacher notes, answer …

• RusFinChain: A Russian Benchmark for Verifiable Chain-of-Thought Reasoning in Finance with Fuzzy-Aligned Evaluation

  M. K. Arabov · 3. Juli 2026 · Explainable Artificial Intelligence (XAI)

  Multi-step symbolic reasoning is essential for robust financial analysis, yet most benchmarks neglect intermediate reasoning steps. FINCHAIN introduced verifiable Chain-of-Thought (CoT) evaluation but is limited to English. FINESSE-Bench includes a Russian block but relies on multiple-choice questio…

• Training Vision-Language-Action Models with Dense Embodied Chain-of-Thought Supervision

  Haoyang Li, Guanlin Li, Youhe Feng, Chen Zhao, Zhuoran Wang, Yang Li, Qizhe Wei, Shifeng Bao, Haitao Shen, Yihan Zhao, Tong Yang, Jing Zhang · 30. Juni 2026 · Multimodal Machine Learning Applications

  Cross-embodiment transfer in vision-language-action (VLA) models remains challenging because low-level state and action spaces differ fundamentally across robot platforms. We observe that the high-level cognitive process underlying manipulation, including scene perception, object identification, tas…

• Does Verbose Chain-of-Thought Really Help? In-Distribution Evidence that Content, Not Length, Matters

  Wenlong Wang, Fergal Reid · 30. Juni 2026 · Large Language Models

  Chain-of-thought (CoT) prompting improves LLM reasoning, but the source is contested: do the intermediate steps help because they carry useful semantic content, or because conditioning on more tokens buys extra computation before the model commits to an answer? We bring two lines of evidence to bear…

• X-Mind: Efficient Visual Chain-of-Thought via Predictive World Model for End-to-End Driving

  Bohao Zhao, Chengrui Wei, Guangfeng Jiang, Ruixin Liu, Xuejie Lv, Liu Liang, Sutao Deng, Xiuyang Fan, Pengkun Zheng, Jinyun Zhou, Rui Guo, Hanpeng Liu, Yutong Zheng, Yi Guo, Xinlong Zheng, Qingyu Luo, Zhuangzhuang Ding, Yu Zhang, Hang Zhang, Xianming Liu · 30. Juni 2026 · Multimodal Machine Learning Applications

  Predicting future states is essential for autonomous agents, yet current Vision-Language-Action (VLA) models fundamentally lack this capability, relying instead on reactive perception-action mapping. While integrating Predictive World Models (PWMs) addresses this gap, existing approaches either incu…

• Zero-shot Tweet-Level Stance Detection Enhanced by External Knowledge and Reflective Chain-of-Thought Reasoning

  Yiju Huang, Wenxian Wang, Lijun Zhou, Rui Tang, Xiao Lan, Tao Zhang, Haizhou Wang · 26. Juni 2026 · Large Language Models

  Zero-shot tweet-level stance detection confronts two primary challenges: (1) mitigating the context sparsity inherent in short texts, and (2) establishing the relevance between implicit targets and textual content. While existing methods primarily focus on incorporating external knowledge, they negl…

• PointVG-R: Internalizing Geometric Reasoning in MLLMs for Precise Pointing Localization via Visual Chain of Thought

  Ling Li, Bowen Liu, Zinuo Zhan, Jianhui Zhong, Ziyu Zhu, Bingcai Wei, Kenglun Chang, Zhidong Deng · 24. Juni 2026 · Multimodal Machine Learning Applications

  Pointing-based visual grounding requires models to precisely locate target objects by deciphering complex spatial relationships between the visual scene and pointing gestures. Traditional methods typically encode input images into static feature representations and perform reasoning primarily within…

• IV-CoT: Implicit Visual Chain-of-Thought for Structure-Aware Text-to-Image Generation

  Zixuan Li, Haokun Lin, Yicheng Xiao, Zhiwei Li, Xinyang Song, Zelong Zheng, Yong He, Heng Yao, Ke Ding, Chao Yu, Chuan Yuan, Qi Li, Zhenan Sun · 24. Juni 2026 · Multimodal Machine Learning Applications

  Unified multi-modal large language models (MLLMs) have achieved strong text-to-image generation quality, but still struggle with structure-aware prompt following, where object counts, spatial relations, attribute bindings, and coarse layouts must be preserved. We attribute this limitation in part to…

• When Compression Helps and When It Hurts: Condition-Aware Analysis of Chain-of-Thought Distillation

  Siyang Lyu, Zhijing Sun, Xinghao Chen, Tong Liu, Dawei Zhu, Xiaoyu Shen · 23. Juni 2026 · Embodied and Extended Cognition

  Chain-of-Thought (CoT) distillation transfers multi-step reasoning from large reasoning models to smaller students, but verbose teacher traces inflate both training and inference cost. Existing CoT compression methods fall into two families, selective pruning and generative rewriting, yet prior stud…

• Chains That See, Answers That Don't: A Multi-Aspect Evaluation Recipe for Forced Chain-of-Thought on Video-MME

  Zhichao Fan, Yanhang Li, Zexin Zhuang · 23. Juni 2026 · Multimodal Machine Learning Applications

  Forced chain-of-thought (CoT) is widely assumed to make vision-language models more reliable on video question answering. We propose a small three-probe evaluation recipe to test that assumption: paired accuracy across direct, CoT, answer-first, and no-video conditions; a counterfactual video-swap d…

• Local Causal Attribution of Chain-of-Thought Reasoning

  Dennis Wei, Yannis Belkhiter, Erik Miehling, Radu Marinescu · 23. Juni 2026 · Bayesian Modeling and Causal Inference

  Understanding the causal structure of a language model's thought process is a problem of significant importance for both transparency and safety. In this work, we take a local approach toward this goal by analyzing the causal relationships among individual components, termed units, of a given, speci…

• Look Light, Think Heavy: What Multimodal Chain-of-Thought Reasoning Can and Cannot Do

  Zhuoran Jin, Kejian Zhu, Hongbang Yuan, Yupu Hao, Pengfei Cao, Yubo Chen, Kang Liu, Jun Zhao · 23. Juni 2026 · Multimodal Machine Learning Applications

  Chain-of-Thought (CoT) has become a standard method for improving reasoning capabilities in large language models (LLMs) by eliciting step-by-step thinking, but its effectiveness in multimodal tasks remains unclear. In this paper, we aim to systematically investigate the key question: What can multi…

• A Verifiable Search Is Not a Learnable Chain-of-Thought

  Harsh Patel · 23. Juni 2026 · Big Data and Digital Economy

  It is tempting to assume any task solvable by a short program can be taught to a model as its chain-of-thought: write the steps out, fine-tune, and the model follows. This paper shows the assumption fails for an identifiable class of procedures. The testbed is nine reasoning tasks, each from a deter…

• MammoExpert: Benchmarking Chain-of-Thought Reasoning in Mammography Diagnosis

  Di Dai, Bo Liu, Youcheng Li, Haojun Yu, Zhouhang Bian, Quanlin Wu, Dong Wang, Sichen Meng, Hongye Xuan, Zijie Lan, Shenda Hong, Liwei Wang · 23. Juni 2026 · AI in cancer detection

  Mammography is an essential tool for breast cancer detection, with millions of examinations conducted annually. However, publicly available high-quality mammography datasets for AI development remain limited in both scale and annotation richness, particularly regarding pathological subtype coverage …

• TTFT-Aware Graph Chain-of-Thought:Distance-Indexed Neural A* for Low-Hallucination Multi-Hop Medical Reasoning

  Bechir Dardouri, Ka\"is Zhioua, Yassine Msaddak · 23. Juni 2026 · Advanced Graph Neural Networks

  Hallucinations and opaque reasoning remain unacceptable failure modes for clinical LLMs. We present a production-grade GraphRAG stack that constrains answers to verifiable graph chain-of-thought paths in a heterogeneous, ~700K-node medical knowledge graph powering a fertility assistant. The core ide…

• Can Reasoning Models Detect Changes to their Chains of Thought?

  Sathvik Napa, Utkarsh Singh, Chengyuan Xue, Miriam Wanner, William Walden · 23. Juni 2026 · Logic, Reasoning, and Knowledge

  There are many reasons one may want to edit a model's chain of thought (CoT) -- e.g., to prefill it with reasoning from a stronger model or to remove steps that may yield unsafe outputs. The success of these interventions plausibly depends on a model's inability to notice them, as the model may alte…

• Masked Distillation: Internalizing the Chain-of-Thought in Language Models

  Durgesh Kalwar, Vardhan Palod, Subbarao Kambhampati · 22. Juni 2026 · Multimodal Machine Learning Applications

  Large Reasoning Models (LRMs) produce long, explicit chains of intermediate steps before generating a final answer at inference time. These intermediate traces dominate latency, memory usage, and serving cost, even though the final answer correctness is not causally related to the trace correctness …

• What Makes Effective Supervision in Latent Chain-of-Thought: An Information-Theoretic Analysis

  Xinghao Chen, Chak Tou Leong, Wenjin Guo, Jian Wang, Wenjie Li, Xiaoyu Shen · 19. Juni 2026 · Embodied and Extended Cognition

  Latent Chain-of-Thought (CoT) internalizes reasoning within continuous hidden states, offering a promising alternative to verbose discrete reasoning traces. However, robust latent reasoning remains difficult because outcome supervision provides weak learning signals and leaves latent trajectories pr…

• Efficiently Representing Algorithms With Chain-of-Thought Transformers

  Yanhong Li, Anej Svete, Ashish Sabharwal, William Merrill · 19. Juni 2026 · Complexity and Algorithms in Graphs

  The increasing popularity of \emph{reasoning} models -- language models that output a series of reasoning or thought tokens before producing an answer -- is justified, in part, by theoretical results showing that chain-of-thought (CoT) transformers can simulate Turing machines, and thus perform arbi…

• Universal Image Restoration via Internalized Chain-of-Thought Reasoning

  Yu Guo, Zhengru Fang, Shengfeng He, Senkang Hu, Yihang Tao, Phone Lin, Yuguang Fang · 17. Juni 2026 · Image Enhancement Techniques

  Image restoration seeks to recover high-quality images from degraded inputs but becomes highly ill-posed under complex, mixed degradations. While unified all-in-one models are common, their performance declines as degradation complexity increases. Recent works adopt Chain-of-Thought (CoT) reasoning …

• ttda704 at SemEval-2026 Task 6: Structured Chain-of-Thought Prompting for Political Evasion Detection

  Tai Tran Tan, An Dinh Thien · 16. Juni 2026 · Large Language Models

  This paper describes our system for SemEval-2026 Task 6, which addresses the classification of political evasion strategies in English question-answer pairs extracted from U.S. presidential interviews. We systematically compare two distinct paradigms: (1) Parameter-Efficient Fine-Tuning of Qwen3 mod…

• NeRD: Neuro-Symbolic Rule Distillation for Efficient Ontology-Grounded Chain-of-Thought in Medical Image Diagnosis

  Hongxi Yang, Yiwen Jiang, Siyuan Yan, Jamie Chow, Eunis Li, Charlotte Poon, Stephanie Fong, Xiangyu Zhao, Deval Mehta, Yasmeen George, Zongyuan Ge · 16. Juni 2026 · Explainable Artificial Intelligence (XAI)

  Interpretability is essential for trustworthy medical image diagnosis. However, existing concept-driven interpretable methods have key limitations: Concept Bottleneck Models (CBMs) require scoring all predefined concepts at inference time and for manual intervention, imposing a substantial burden on…

• CoRA: Confidence-Rationale Alignment for Reliable Chain-of-Thought Reasoning

  Juming Xiong, Weixin Liu, Kevin Guo, Congning Ni, Junchao Zhu, Chongyu Qu, Chao Yan, Katherine Brown, Avinash Baidya, Xiang Gao, Bradley Malin, Zhijun Yin · 16. Juni 2026 · Large Language Models

  Chain-of-thought (CoT) reasoning can improve LLM performance, but high answer confidence may be misleading when the accompanying CoT rationale is plausible yet incomplete or poorly supported. We study confidence--rationale alignment: whether a model's confidence in its committed answer is justified …

• Beyond Accuracy: Measuring Bias Acknowledgment in Chain-of-Thought Reasoning for Responsible AI Evaluation

  Xian Sun, Wei Gao, Yingshuo Wang, Lingdong Kong, Yanhang Li, Zhichao Fan, Zexin Zhuang, Wenlong Dong, Zhiyuan Zheng, Hrishikesh Paranjape, Abhishek Mandal, Johnny R. Zhang · 16. Juni 2026 · Explainable Artificial Intelligence (XAI)

  Reasoning models are increasingly used in settings where the final answer is not the only object of review: educational tools may show students intermediate steps, decision-support systems may require human oversight, and audit workflows may inspect traces for misleading or biased input. In such set…