Eliciting Research Taste in LLMs through Future Research Direction Choice
- Published
- Source
- arXiv
- Paper number
- 1478
- Field
- Research Agents
- arXiv ID
- 2611.19794
Key points
- The authors built 80 pairwise comparison queries from 19 ML papers published after model training cutoffs.
- Across 8 models, author alignment ranged from 45.0% to 67.5% and stable divergence from 15.0% to 36.2%.
- 45 of 80 pairs elicited stable divergence from at least one model, totaling 169 divergence events.
- Across four prompt variations, models retained divergences with weighted means from 66.9% to 80.5%.
- In the pilot human study, 58 of 95 fixed-choice responses (61.1%) selected the author-recommended direction.
- The most frequent divergence transition was Infrastructure-to-Methodological substitution with 55 events.
Paper links
External research summaries. These are not HDATF publications or measured product results.