Does Slightly Mean Somewhat? Measuring Vague Intensity Words in LLM Numeric Actions
Quick Take
The study analyzes how language models interpret vague intensity words in numeric actions.
Key Points
- Model compresses 10 intensity words into 5 outputs.
- Starting state influences numeric output more than word choice.
- Behavior varies near operational limits based on word strength.
Reader Mode unavailable (could not extract clean content).
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CL
See more →arXiv cs.CL·Leyao Wang, Yanan He, Peng Chen, Asaf Yehudai, Yixin Liu, Rex Ying, Michal Shmueli-Scheuer, Arman Cohan
2d ago FeaturedOriginal
Time to REFLECT: Can We Trust LLM Judges for Evidence-based Research Agents?
AI Summary
The reliability of LLM judges for evaluating deep research agents is critically assessed using the REFLECT benchmark.