Image de couverture de livre

Eliciting Chain-of-Thought in Base LLMs via Gradient-Based Representation Optimization

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Wang, Zijian, Ma, Yanxiang, Xu, Chang
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

ThoughtProbe: Classifier-Guided LLM Thought Space Exploration via Probing Representations
par: Wang, Zijian, et autres
Publié: (2025)

ThoughtProbe: Classifier-Guided Thought Space Exploration Leveraging LLM Intrinsic Reasoning
par: Wang, Zijian, et autres
Publié: (2025)

Strategic Chain-of-Thought: Guiding Accurate Reasoning in LLMs through Strategy Elicitation
par: Wang, Yu, et autres
Publié: (2024)

Chain-of-Conceptual-Thought Elicits Daily Conversation in Large Language Models
par: Gu, Qingqing, et autres
Publié: (2025)

Graph-Based Chain-of-Thought Pruning for Reducing Redundant Reflections in Reasoning LLMs
par: Yuan, Hongyuan, et autres
Publié: (2026)

Chain of Preference Optimization: Improving Chain-of-Thought Reasoning in LLMs
par: Zhang, Xuan, et autres
Publié: (2024)

ThinkPrune: Pruning Long Chain-of-Thought of LLMs via Reinforcement Learning
par: Hou, Bairu, et autres
Publié: (2025)

Long-Short Chain-of-Thought Mixture Supervised Fine-Tuning Eliciting Efficient Reasoning in Large Language Models
par: Yu, Bin, et autres
Publié: (2025)

SoftCoT: Soft Chain-of-Thought for Efficient Reasoning with LLMs
par: Xu, Yige, et autres
Publié: (2025)

DiffCoT: Diffusion-styled Chain-of-Thought Reasoning in LLMs
par: Cao, Shidong, et autres
Publié: (2026)

Beyond Chain-of-Thought: A Survey of Chain-of-X Paradigms for LLMs
par: Xia, Yu, et autres
Publié: (2024)

GeoSteer: Faithful Chain-of-Thought Steering via Latent Manifold Gradients
par: Kazama, Kentaro, et autres
Publié: (2026)

Mind's Eye of LLMs: Visualization-of-Thought Elicits Spatial Reasoning in Large Language Models
par: Wu, Wenshan, et autres
Publié: (2024)

Optimizing Chain-of-Thought Reasoners via Gradient Variance Minimization in Rejection Sampling and RL
par: Yao, Jiarui, et autres
Publié: (2025)

Efficient Reasoning for LLMs through Speculative Chain-of-Thought
par: Wang, Jikai, et autres
Publié: (2025)

Keypoint-based Progressive Chain-of-Thought Distillation for LLMs
par: Feng, Kaituo, et autres
Publié: (2024)

CoT-BERT: Enhancing Unsupervised Sentence Representation through Chain-of-Thought
par: Zhang, Bowen, et autres
Publié: (2023)

Direct Value Optimization: Improving Chain-of-Thought Reasoning in LLMs with Refined Values
par: Zhang, Hongbo, et autres
Publié: (2025)

Implicit Sentiment Analysis Based on Chain of Thought Prompting
par: Duan, Zhihua, et autres
Publié: (2024)

Eliciting Uncertainty in Chain-of-Thought to Mitigate Bias against Forecasting Harmful User Behaviors
par: Sicilia, Anthony, et autres
Publié: (2024)

Short Chains, Deep Thoughts: Balancing Reasoning Efficiency and Intra-Segment Capability via Split-Merge Optimization
par: Gui, Runquan, et autres
Publié: (2026)

Scheherazade: Evaluating Chain-of-Thought Math Reasoning in LLMs with Chain-of-Problems
par: Miner, Stephen, et autres
Publié: (2024)

Efficient Reasoning via Chain of Unconscious Thought
par: Gong, Ruihan, et autres
Publié: (2025)

Legal$Δ$: Enhancing Legal Reasoning in LLMs via Reinforcement Learning with Chain-of-Thought Guided Information Gain
par: Dai, Xin, et autres
Publié: (2025)

BC Protocol: Structured Dual-Expert Dialogue for Eliciting High-Quality Chain-of-Thought Post-Training Data
par: Zou, Bo, et autres
Publié: (2026)

Unlocking the Capabilities of Thought: A Reasoning Boundary Framework to Quantify and Optimize Chain-of-Thought
par: Chen, Qiguang, et autres
Publié: (2024)

S3-CoT: Self-Sampled Succinct Reasoning Enables Efficient Chain-of-Thought LLMs
par: Du, Yanrui, et autres
Publié: (2026)

TokenSkip: Controllable Chain-of-Thought Compression in LLMs
par: Xia, Heming, et autres
Publié: (2025)

Thoughts-as-Planning: Latent World Models for Chain-of-Thoughts Optimization via Reinforcement Planning
par: Liu, Dong, et autres
Publié: (2026)

Chain-of-Defensive-Thought: Structured Reasoning Elicits Robustness in Large Language Models against Reference Corruption
par: Wang, Wenxiao, et autres
Publié: (2025)

Demystifying Long Chain-of-Thought Reasoning in LLMs
par: Yeo, Edward, et autres
Publié: (2025)

Faithful Logical Reasoning via Symbolic Chain-of-Thought
par: Xu, Jundong, et autres
Publié: (2024)

Evaluating GRPO and DPO for Faithful Chain-of-Thought Reasoning in LLMs
par: Mohammadi, Hadi, et autres
Publié: (2025)

Compressed Chain of Thought: Efficient Reasoning Through Dense Representations
par: Cheng, Jeffrey, et autres
Publié: (2024)

On the Representational Capacity of Neural Language Models with Chain-of-Thought Reasoning
par: Nowak, Franz, et autres
Publié: (2024)

Unlocking General Long Chain-of-Thought Reasoning Capabilities of Large Language Models via Representation Engineering
par: Tang, Xinyu, et autres
Publié: (2025)

Optimizing Chain-of-Thought Reasoning: Tackling Arranging Bottleneck via Plan Augmentation
par: Qiu, Yuli, et autres
Publié: (2024)

Self-Training with Direct Preference Optimization Improves Chain-of-Thought Reasoning
par: Wang, Tianduo, et autres
Publié: (2024)

RAT: Retrieval Augmented Thoughts Elicit Context-Aware Reasoning in Long-Horizon Generation
par: Wang, Zihao, et autres
Publié: (2024)

Upfront Chain-of-Thought: A Cooperative Framework for Chain-of-Thought Compression
par: Li, Chengzhengxu, et autres
Publié: (2025)