Capability Self-Assessment in Large Language Models
cs.AI
Submitted: 2026-05-29
Updated: 2026-09-26
Comments: 46 pages, 17 figures, 24 tables
Code: https://github.com/Joyyang158/llm-csa
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- A Survey on Data Selection for Language Models
- No Answer Needed: Predicting LLM Answer Accuracy from Question-Only Linear Probes
- Mind the Confidence Gap: Overconfidence, Calibration, and Distractor Effects in Large Language Models
- AnyTool: Self-Reflective, Hierarchical Agents for Large-Scale API Calls
- ReTool: Reinforcement Learning for Strategic Tool Use in LLMs
- Data Selection via Optimal Control for Language Models
- MASH: Modeling Abstention via Selective Help-Seeking
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- MetaTool Benchmark for Large Language Models: Deciding Whether to Use Tools and Which to Use
- Language Models (Mostly) Know What They Know
- Semantic Entropy Probes: Robust and Cheap Hallucination Detection in LLMs
- Conformal Prediction with Large Language Models for Multi-Choice Question Answering
- Tulu 3: Pushing Frontiers in Open Language Model Post-Training
- Let's Verify Step by Step
- WebGPT: Browser-assisted question-answering with human feedback
- Conformal Language Modeling
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Large Language Models are overconfident and amplify human bias
- Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs
- On the Tool Manipulation Capability of Open-source Large Language Models
Related papers
- 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
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems