Theme of inquiry
What signals most reliably capture user preferences for recommendations?
A question within its area, explored through 3 lines of inquiry below — each a family of specific questions the research asks.
31 specific questions
- Can prompting strategies eliminate systematic biases without shuffling or aggregation?
- How does output variability disguise confirmation bias in prompt refinement?
- Can forcing warrant checking through structured prompts improve LLM reasoning?
- Can prompt engineering alone defeat LLM politeness bias in review tasks?
- Can prompt-based debiasing overcome entrenched LLM model priors?
- Can LLM-generated descriptions of schemes outperform formal dictionary definitions for prompting?
- Does argument-scheme prompting improve reasoning in non-code domains the same way?
74 specific questions
- Can prompt optimization alone inject knowledge models don't already have?
- Can prompting techniques reliably force models to enumerate hidden constraints?
- Can prompt engineering improve reasoning or only move requests into denser regions?
- Can users inject entirely new knowledge into models through prompting alone?
- Can prompt optimization inject new knowledge into language models?
- Can prompting alone inject new domain knowledge into a model?
- Can prompting inject new knowledge into already-trained AI models?
34 specific questions
- Can inference budgets be allocated adaptively based on prompt difficulty?
- How should inference budgets adapt based on prompt difficulty?
- What makes inference budgets allocate adaptively per prompt difficulty?
- How should inference compute budget be allocated across different prompt difficulties?
- How should we allocate compute between reasoning and retrieval iterations?
- Can compute-optimal scaling work without co-optimizing the prompt itself?
- Can inference budgets be allocated differently based on prompt difficulty?