LLM Abstention Can Be a Prompt Artifact, in Addition to Genuine Uncertainty
Large Language Models (LLMs) are increasingly trained to abstain from answering questions they are unsure about. However, this ability is often misused: in real-world applications, input prompts sometimes contain uncertainty elements, and driven by this, LLMs are inclined to abstain even on problems they are capable of solving. We argue that LLM abstention is not only an expression of genuine uncertainty; it is also an artifact that can be largely influenced by prompts. We name this phenomenon *Abstention Inflation*. We add "Unknown" as an extra option for LLMs to choose from; experiments show serious accuracy drops on True/False Questions (TFQs). Replacing "Unknown" with an unrelated random word produces an identical effect. We argue that LLMs are trained to imitate the surface pattern of *abstention*, rather than to express genuine uncertainty. Based on ten experiments, we support four claims that form a progressive argument: (C1) *Abstention Inflation* is triggered by the structural presence of an extra option, not by genuine uncertainty; (C2) further, it makes the model deny it can answer even when it can; (C3) at the representation level, this manifests as a later-layer output override; (C4) finally, this bias is stable and emerges through instruction tuning, rather than stochastic noise.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Mind the Gap: How Elicitation Protocols Shape the Stated-Revealed Preference Gap in Language Models
Recent work identifies a stated-revealed (SvR) preference gap in language models (LMs): a mismatch between the values models endorse and the choices they make in context. Existing evaluations rely heavily on binary force…
Confidential Guardian: Cryptographically Prohibiting the Abuse of Model Abstention
Cautious predictions -- where a machine learning model abstains when uncertain -- are crucial for limiting harmful errors in safety-critical applications. In this work, we identify a novel threat: a dishonest institution…
I-CALM: Incentivizing Confidence-Aware Abstention for LLM Hallucination Mitigation
Large language models (LLMs) frequently produce confident but incorrect answers, partly because common binary scoring conventions reward answering over honestly expressing uncertainty. We study whether prompt-only interv…
AbstentionBench: Reasoning LLMs Fail on Unanswerable Questions
For Large Language Models (LLMs) to be reliably deployed in both everyday and high-stakes domains, knowing when not to answer is equally critical as answering correctly. Real-world user queries, which can be underspecifi…
MathKnowing When to Abstain: Medical LLMs Under Clinical Uncertainty
Current evaluation of large language models (LLMs) overwhelmingly prioritizes accuracy; however, in real-world and safety-critical applications, the ability to abstain when uncertain is equally vital for trustworthy depl…
Question Answering