LLM Abstention Can Be a Prompt Artifact, in Addition to Genuine Uncertainty
cs.CL
Submitted: 2025-07-22
Updated: 2026-09-30
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- FinSafetyBench: Evaluating LLM Safety in Real-World Financial Scenarios
- Fine-tuning Large Language Models for Improving Factuality in Legal Question Answering
- Uncertainty in Language Models: Assessment through Rank-Calibration
- What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Exams
- Language Models (Mostly) Know What They Know
- AbstentionBench: Reasoning LLMs Fail on Unanswerable Questions
- FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance
- Knowledge Boundary of Large Language Models: A Survey
- Deep reinforcement learning from human preferences
- FRoG: Evaluating Fuzzy Reasoning of Generalized Quantifiers in Large Language Models
- Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
- LogiQA: A Challenge Dataset for Machine Reading Comprehension with Logical Reasoning
- FOLIO: Natural Language Reasoning with First-Order Logic
- Knowing When to Abstain: Medical LLMs Under Clinical Uncertainty
- Enhancing Reasoning Capabilities of LLMs via Principled Synthetic Logic Corpus
- Measuring Massive Multitask Language Understanding
- RefusalBench: Generative Evaluation of Selective Refusal in Grounded Language Models
- Training language models to follow instructions with human feedback
- Direct Preference Optimization: Your Language Model is Secretly a Reward Model
- Self-Evaluation Improves Selective Generation in Large Language Models
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