Strong yet Controllable LLM Abstention without Learning to Abstain
cs.CL
Submitted: 2026-10-12
Updated: 2026-10-12
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- gpt-oss-120b & gpt-oss-20b Model Card
- Abstention as an Action Can Kill Both the Reward Gradient and the KL Anchor: Collapse Law and Repair for Error-Penalized Reinforcement Learning
- The Llama 3 Herd of Models
- Language Models (Mostly) Know What They Know
- Honesty over Accuracy: Trustworthy Language Models through Reinforced Hesitation
- TIAR: Trajectory-Informed Advantage Reweighting for LLM Abstention Learning
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Mitigating LLM Hallucination via Behaviorally Calibrated Reinforcement Learning
- Qwen3 Technical Report
- Qwen2.5 Technical Report
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