Line of inquiry
Inquiring lines›What explains language model reaso…›Why do models produce unreliable r…›this line of inquiry
How does improved reasoning affect models' ability to acknowledge uncertainty?
A broader line of inquiry — a family of 49 specific questions the research asks around this. Follow one into its inquiring-line page, or move sideways to a related line below.
Questions in this line of inquiry 49
Specific inquiring lines the field asks around this — ordered from the most general framing down to the most specific angle.
- How do reasoning improvements suppress a model's ability to abstain?
- Does reasoning fine-tuning actually reduce a model's ability to abstain?
- Can models learn to stop thinking when a question lacks necessary information?
- Does reasoning fine-tuning actually harm a model's ability to abstain?
- Does reasoning fine-tuning actually damage a model's ability to abstain?
- Can models identify information gaps without just guessing or refusing to answer?
- Can models learn to ask clarifying questions instead of making assumptions?
- Why does reasoning fine-tuning reduce a model's ability to abstain?
- Does training for better reasoning reduce an AI system's ability to abstain?
- Why does reasoning fine-tuning reduce models' ability to abstain?
- Can LLMs learn to ask clarifying questions instead of guessing?
- Do models trained for reasoning lose their ability to decline questions?
- Can models learn to ask clarifying questions instead of answering prematurely?
- Why do reasoning models confidently generate wrong answers instead of abstaining?
- Can reasoning models reject ill-posed questions or do they overthink?
- Can proactive critical thinking alone enable models to request clarification effectively?
- Do models naturally learn to ask clarifying questions without explicit supervision?
- Why does reasoning fine-tuning reduce model abstention capacity by 24 percent?
- Why do language models naturally under-abstain instead of over-abstain?
- Can models learn to identify what information is missing from questions?
- Does reasoning training actively undermine the abstention capacity safety training created?
- How should safety training and reasoning training balance abstention differently?
- What training approach enables models to proactively request clarification?
- When models lack representation depth, does refusal look identical to safety-driven over-abstention?
- How does expressing uncertainty help models avoid the answer-or-abstain dilemma?
- Can language systems learn when to ask for clarification instead of choosing one reading?
- What makes a model refuse to answer without evidence present?
- What happens when reasoning fine-tuning eliminates model refusal mechanisms entirely?
- Can models identify what information they are missing in underspecified tasks?
- Can models identify what information they are missing in underspecified problems?
- How does proactive critical thinking enable models to identify missing information?
- What structural changes enable agents to ask clarifying questions?
- What makes abstention a learnable behavior instead of a default penalty?
- Can proactive critical thinking train models to request clarification actively?
- Why do models detect false assumptions but still fail to correct them appropriately?
- Why do models struggle with asking questions in multi-turn conversational reasoning tasks?
- Can dialogue systems abstain from responding when uncertainty is too high?
- Can explicit rejection responses solve the over-specialization failure mode?
- Why do models confirm seeing hints but rarely mention them unprompted?
- What training signals would teach models when not to reason?
- Can AI systems identify important unanswered questions that emerge during reasoning?
- Why do weaker language models fail at multi-turn strategic questioning?
- Why do safety-trained models refuse questions they could actually answer well?
- How does proactive critical thinking detect when information is incomplete?
- How can agents detect missing information before attempting to solve problems?
- Can models distinguish between ambiguous and incomplete information inputs?
- How does ambiguity detection connect to models' ability to ask clarifying questions?
- How do models decide between refusing or hallucinating?
- Can abstention behavior transfer from small models to frontier models?