Chain of Faith: Policy-Internal Rewards for Reasoning Reliance
cs.AI, cs.LG
Submitted: 2026-11-02
Updated: 2026-11-02
Terminology
Sources
- Measuring and curing reasoning rigidity: from decorative chain-of-thought to genuine faithfulness
- Mitigating Shortcut Reasoning in Language Models: A Gradient-Aware Training Approach
- Reasoning Models Don't Always Say What They Think
- Training Verifiers to Solve Math Word Problems
- Truthful or Fabricated? Using Causal Attribution to Mitigate Reward Hacking in Explanations
- Counterfactual Simulation Training for Chain-of-Thought Faithfulness
- Rethinking Reasoning Quality in Large Language Models through Enhanced Chain-of-Thought via RL
- Likelihood-Based Reward Designs for General LLM Reasoning
- Measuring Faithfulness in Chain-of-Thought Reasoning
- Stop Rewarding Hallucinated Steps: Faithfulness-Aware Step-Level Reinforcement Learning for Small Reasoning Models
- Qwen2.5 Technical Report
- Question Decomposition Improves the Faithfulness of Model-Generated Reasoning
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- LIFT: Likelihood-Based Intervention Faithfulness Training
- CTRL-RAG: Contrastive Likelihood Reward Based Reinforcement Learning for Context-Faithful RAG Models
- Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting
- Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
- Beyond Correctness: Rewarding Faithful Reasoning in Retrieval-Augmented Generation
- Mechanistic Evidence for Faithfulness Decay in Chain-of-Thought Reasoning
- Why Models Know But Don't Say: Chain-of-Thought Faithfulness Divergence Between Thinking Tokens and Answers in Open-Weight Reasoning Models
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents