Shared Experience, Separate Learning: Companion Confidence Calibration for LLMs
cs.CL
Submitted: 2026-09-27
Updated: 2026-09-27
Code: https://github.com/THUDM/slime
Terminology
Sources
- The Internal State of an LLM Knows When It's Lying
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Gaussian Error Linear Units (GELUs)
- Language Models (Mostly) Know What They Know
- Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation
- Teaching Models to Express Their Uncertainty in Words
- C$^2$GSPG: Confidence-calibrated Group Sequence Policy Gradient towards Self-aware Reasoning
- AgentAbstain: Do LLM Agents Know When Not to Act?
- Agentic Abstention: Do Agents Know When to Stop Instead of Act?
- Decoupling Reasoning and Confidence: Resurrecting Calibration in Reinforcement Learning from Verifiable Rewards
- When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories
- When Do LLMs Need Retrieval Augmentation? Mitigating LLMs' Overconfidence Helps Retrieval Augmentation
- Popular but Wrong: Understanding and Mitigating LLM Overconfidence through Knowledge Popularity
- Annotation-Efficient Universal Honesty Alignment
- Towards Fully Exploiting LLM Internal States to Enhance Knowledge Boundary Perception
- SQuAD: 100,000+ Questions for Machine Comprehension of Text
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Unsupervised Real-Time Hallucination Detection based on the Internal States of Large Language Models
- Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedback
- Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering