Search: chain of thought

520 papers found.

• Robust Dual-Signal Fusion: Hybrid Neuro-Symbolic Gating with Compressed Chain-of-Thought Refinement for Irony Detection in Social Media Texts

  Ankit Bhattacharjee, Krityapriya Bhaumik · 16 June 2026 · Sentiment Analysis and Opinion Mining

  Large Language Models (LLMs) natively default to literal semantic interpretations, making zero-shot irony detection a persistent challenge. We introduce the Robust Dual-Signal (RDS) Fusion framework, a hybrid neuro-symbolic architecture that compresses Chain-of-Thought (CoT) reasoning trajectories w…

• Gen-VCoT: Generative Visual Chain-of-Thought Reasoning via Diffusion-Based RGB Intermediate Representations

  Zhiqiang Zhou, Junliang Dai, Xu ling · 16 June 2026 · Multimodal Machine Learning Applications

  Multimodal large language models (MLLMs) excel at visual reasoning but rely on text-based chain-of-thought (CoT), lacking interpretable visual intermediates. Existing methods use opaque tokens or external tools, missing key properties. We propose Gen-VCoT, a framework using expert vision models to g…

• Adapting Reinforcement Learning with Chain-of-Thought Supervision for Explainable Detection of Hateful and Propagandistic Memes

  Mohamed Bayan Kmainasi, Mucahid Kutlu, Ali Ezzat Shahroor, Abul Hasnat, Firoj Alam · 16 June 2026 · Misinformation and Its Impacts

  Hateful and propagandistic memes exploit the interplay between images and text to convey harmful intent that neither modality reveals alone. Although thinking-based multimodal large language models (MLLMs) have advanced vision-language understanding, their application to meme content moderation rema…

• RoboPIN: Grounded Embodied Reasoning via Pinned Chain-of-Thought

  Yaoting Huang, Yifu Yuan, Linqi Han, Chengwen Li, Shuoheng Zhang, Xianze Yao, Hongyao Tang, Yan Zheng, Jianye Hao · 16 June 2026 · Multimodal Machine Learning Applications

  Embodied reasoning requires models to perceive task-relevant objects and spaces in physical environments and maintain consistent visual grounding throughout multi-step reasoning. However, current vision-language models rely on text-only or coordinate-augmented chain-of-thought, where entity referenc…

• Fractured Chain-of-Thought Reasoning

  Baohao Liao, Hanze Dong, Yuhui Xu, Doyen Sahoo, Christof Monz, Junnan Li, Caiming Xiong · 15 June 2026 · Multi-Agent Systems and Negotiation

  Inference-time scaling techniques have significantly bolstered the reasoning capabilities of large language models (LLMs) by harnessing additional computational effort at inference without retraining. Similarly, Chain-of-Thought (CoT) prompting and its extension, Long CoT, improve accuracy by genera…

• Beyond the Commitment Boundary: Probing Epiphenomenal Chain-of-Thought in Large Reasoning Models

  Daniel Scalena, Sara Candussio, Luca Bortolussi, Elisabetta Fersini, Malvina Nissim, Gabriele Sarti · 12 June 2026 · Neurobiology of Language and Bilingualism

  Chain-of-thought (CoT) reasoning is the dominant paradigm for inference-time scaling in language models, yet the causal influence of individual steps on the final answer poorly understood. We estimate each step's causal importance via early exit and use this measure to study how answers form across …

• NTS-CoT: Mitigating Hallucinations in LLM-based News Timeline Summarization with Chain-of-Thought Reasoning

  Feng Lyu, Huiqin Yan, Sijing Duan, Hao Wu, Shuang Gu, Xue Qiao, Weixu Zhang, Haolun Wu · 12 June 2026 · Large Language Models

  The rapid updates of online news make tracking event developments challenging, highlighting the need for timeline summarization (TLS). Hallucinations, where LLM-generated content deviates from source news, still remain a critical issue in LLM-based TLS and are not well studied in existing works. To …

• Calibration Drift Under Reasoning: How Chain-of-Thought Budgets Induce Overconfidence in Large Language Models

  Prakul Sunil Hiremath, Harshit R. Hiremath · 11 June 2026 · Explainable Artificial Intelligence (XAI)

  The ability of large language models (LLMs) to express calibrated uncertainty is important for safe deployment. Chain-of-thought (CoT) reasoning is widely used to improve accuracy and reliability, but its effect on calibration is not fully understood. We show that this picture is incomplete: in some…

• Why Does Reasoning Length Converge? Unveiling the Underfitting-Overfitting Trade-off in Chain-of-Thought

  Zeyu Gan, Hao Yi, Yong Liu · 10 June 2026 · Large Language Models

  Test-time scaling, primarily manifested through multi-step Chain-of-Thought (CoT) reasoning via Reinforcement Learning (RL), has emerged as a pivotal paradigm for enhancing the reasoning capabilities of Large Language Models (LLMs). However, a significant theoretical gap persists: traditional token-…

• When the Chain of Thought Knows Better: Failure Modes in Multi-Turn Reasoning Models

  Sai Kartheek Reddy Kasu, Nils Lukas, Samuele Poppi · 10 June 2026 · Large Language Models

  Failures in multi-turn reasoning models are largely invisible to terminal-score evaluation. A model can lock onto an unsafe stance early in a long dialogue, yet its final-turn refusal rate may appear indistinguishable from a robustly aligned baseline. To expose these hidden temporal dynamics, we pro…

• TVI-CoT: Text-Visual Interleaved Chain-of-Thought Reasoning for Multimodal Understanding

  Lianyu Hu, Xiaoyu Ma, Zeqin Liao, Yang Liu · 9 June 2026 · Multimodal Machine Learning Applications

  Chain-of-thought (CoT) reasoning has proven effective for enhancing problem-solving in large language models. However, when applied to multimodal LLMs (MLLMs), existing CoT approaches suffer from a fundamental limitation: they perform reasoning entirely in text without accessing visual features duri…

• VTI-CoT: Visual-Textual Interleaved Chain of Thought for Video Reasoning

  Shufan Zhang, Ziyue Lin, Bairun Wang, Lei Jin, Xuanding Ding, Xinzhu Ma, Kunlin Yang · 5 June 2026 · Multimodal Machine Learning Applications

  Video reasoning aims to understand complex temporal events and causal relationships within videos. Recently, Chain-of-Thought (CoT) has been introduced to this field to enhance reasoning accuracy. However, existing CoT-based video reasoning methods primarily rely on text-only information for logical…

• Entity Binding Failures in Speech LLM Reasoning: Diagnosis and Chain-of-Thought Intervention

  Ming-Hao Hsu, Xiaohai Tian, Jun Zhang, Zhizheng Wu · 4 June 2026 · Large Language Models

  Speech Large Language Models (SLLMs) underperform their text counterparts on complex reasoning. We reveal that this gap is not a uniform cognitive deficit. Evaluating two architecturally diverse SLLMs, we show speech-to-text (S2T) matches or exceeds text-to-text (T2T) on spatial, syntactic, and fact…

• Can Reasoning Path still be Effective as Input? Bridging Post-Reasoning to Chain-of-Thought Compression

  Chengzhengxu Li, Xiaoming Liu, Zhaohan Zhang, Shengchao Liu, Guoxin Ma, Yu Lan, Cong Wang, Chao Shen · 4 June 2026 · Large Language Models

  Recent developments have enabled advanced reasoning in Large Language Models (LLMs) via long Chain-of-Thought (CoT), trading efficiency during inference for performance. Existing works focus on compressing generated CoT in reasoning, which impairs the necessary information for deriving the correct a…

• Selection-Aware Diagnostics for Chain-of-Thought Answer Hijacking

  Jianwei Tai · 4 June 2026 · Adversarial Robustness in Machine Learning

  We study a controlled numeric proxy for chain-of-thought (CoT) answer hijacking, motivated by attacks in which benign-looking reasoning steers a harmful final answer. CoT wrappers on GSM8K and MATH-500 flip final answers away from gold labels. Rather than treating activation patching as clean-trace …

• HybridThinker: Efficient Chain-of-Thought Reasoning via Compressed Memory and Transient Thought Steps

  Xin Liu, Runsong Zhao, Xinyu Liu, Junhao Ruan, Pengcheng Huang, Shichao Dong, Chunyang Xiao, Chenglong Wang, Changliang Li, Jingbo Zhu, Tong Xiao · 3 June 2026 · Generative Adversarial Networks and Image Synthesis

  Extended chain-of-thought (CoT) traces improve LLM reasoning but incur substantial computational and memory costs. While existing CoT compression methods mitigate this by condensing thought steps into compact representations via memory tokens and retaining only these representations at inference tim…

• An Asymptotic Theory of Chain-of-Thought in In-Context Learning

  Kaito Takanami, Cengiz Pehlevan · 3 June 2026 · Neurobiology of Language and Bilingualism

  Chain-of-thought (CoT) reasoning has become a widely used mechanism for eliciting multi-step reasoning in large language models by generating intermediate reasoning steps at inference time. Yet the scaling behavior of generalization with CoT depth remains poorly understood. To address this question,…

• Agentic Chain-of-Thought Steering for Efficient and Controllable LLM Reasoning

  Yu Xia, Zhouhang Xie, Xin Xu, Byungkyu Kang, Prarit Lamba, Xiang Gao, Julian McAuley · 3 June 2026 · Large Language Models

  Large language models improve final-answer accuracy through extended chain-of-thought reasoning, but often spend tokens inefficiently and offer little inference-time control. Existing efficient reasoning methods control thinking length by shortening, early-stopping, or compressing traces, leaving ho…

• Attention-guided Fine-tuning of Multimodal Large Language Models Improves Chain-of-Thought Reasoning

  Sanchit Sinha, Guangzhi Xiong, Bohan Liu, Zhenghao He, Aidong Zhang · 2 June 2026 · Multimodal Machine Learning Applications

  The effectiveness of Chain-of-Thought (CoT) prompting in Multimodal Large Language Models (MLLMs) remains uncertain: across several visual reasoning benchmarks, CoT prompting often degrades performance compared to direct prompting. In this paper, we provide a systematic analysis of CoT behavior in t…

• Unveiling the Entropy Dynamics of Chain-of-Thought Reasoning

  Ting Xu, Xu He, Yupu Lu, Jiankai Sun, Dong Li, Wai Lam, Jianye Hao · 2 June 2026 · Embodied and Extended Cognition

  This paper investigates the entropy dynamics of Chain-of-Thought (CoT) and uncovers a consistent two-phase structure: an Uncertainty Region of exploration transitioning sharply to a Confidence Region of convergence. We demonstrate that the Confidence Region possesses two critical properties: 1) High…

• HMPO: Hybrid Median-length Policy Optimization for Chain-of-Thought Compression

  Minghui Zheng, Hongxu Chen, Huimin Ren, Hongsheng Xin, Xiaoyang Qu, Ze Wang, Shuling Yang, Ziyu Peng, Kaike Zhang, Pan Zhou, Kun Zhan · 2 June 2026 · Large Language Models

  Large language models achieve remarkable performance via extended chain-of-thought (CoT) reasoning, yet this lengthy process incurs substantial inference overhead. Existing CoT compression methods struggle with inflexible manual length budgets, computationally expensive multi-stage training pipeline…

• Diversity Over Frequency: Rethinking Tool Use in Visual Chain-of-Thought Agents

  Dong-Hee Kim, Reuben Tan, Donghyun Kim · 2 June 2026 · Multimodal Machine Learning Applications

  Visual agents employ external visual tools within visual chains of thought to incorporate fine-grained evidence. While prior work has mainly studied these tools in visual search tasks, their role in more complex visual reasoning remains underexplored. In this paper, we move beyond simple visual sear…

• CSRP: Chain-of-Thought Reasoning for Chinese Text Correction via Reinforcement Learning with Efficiency-Aware Rewards

  Wei Tian, Yuhao Zhou, Man Lan · 2 June 2026 · Natural Language Processing Techniques

  Large Language Model (LLM) based Chinese Grammatical Error Correction (CGEC) systems face two critical challenges: general-purpose models lack specialized linguistic priors for subtle grammatical distinctions, and Supervised Fine-Tuning (SFT) with Maximum Likelihood Estimation fails to optimize for …

• Chain-of-Thought and Compressed Looped Transformers: A Memory-Budget Separation

  Haozhou Zhang · 1 June 2026 · Parallel Computing and Optimization Techniques

  Chain-of-thought prompting and looped Transformers both give a fixed model more test-time computation, but they differ in what they remember. Chain-of-thought stores intermediate state in generated tokens that remain in the context, whereas a looped Transformer carries state through recurrent hidden…

• Chain-of-Thought Reasoning In The Wild Is Not Always Faithful

  Iv\'an Arcuschin, Jett Janiak, Robert Krzyzanowski, Senthooran Rajamanoharan, Neel Nanda, Arthur Conmy · 1 June 2026 · Explainable Artificial Intelligence (XAI)

  Recent studies indicate that when faced with explicit biases in prompts, models often omit mentioning these biases in their Chain-of-Thought (CoT) output, revealing that verbalized reasoning can give an incorrect picture of how models arrive at conclusions (unfaithfulness). In this work, we show tha…