SmoothScore: SOTA LLMs still 'smooth' nuanced research findings into overclaims
gregd_nlp · x · 2026-11-06
LLMs hallucinate less than before, but Tiasa's work identifies a persistent error called "smoothing": an LLM reading papers may conclude "method A beats method B" even when the papers show cases where B wins. The team introduces SmoothScore to quantify the effect, showing SOTA models still oversimplify mixed, conditional findings into stronger and broader claims.
More from Research
- Frank Nielsen's taxonomy maps every distance and divergence from Euclidean to quantum geometry — pickover · 2026-11-06
- Anthropic report's key estimates are "guesses" — framing hides massive uncertainty, researcher says — daveholtz · 2026-11-06
- Project AURORA: a big-bet AI Cancer Co-scientist initiative launches with CRUK and NCI backing — zakkohane · 2026-11-06
- PNAS paper: kids explore farther than RL agents, driven by empowerment not info gain — _akpiper · 2026-11-06
- Google open-sources Agile Deliberation, an AI framework that turns fuzzy classification rules into explicit ones — aigclink · 2026-11-06
- ETH RSL's ACP humanoid: reference-free contact planning runs onboard at 50Hz — ChongZzZhang · 2026-11-06