Good Papers

Showing papers from Imperial College London & Thomson Reuters Show all papers

91%Must read
?Must readVote to see the score
NeurIPS 2026U Tübingen Helmholtz MunichTechnische Universität MünchenImperial College London & ThLLM evaluation & benchmarks

CapTrack: Multifaceted Evaluation of Forgetting in LLM Post-Training

CapTrack defines LLM post-training forgetting as systematic behavioral drift rather than only factual loss, finding instruction tuning causes the strongest drift and no universal mitigation exists.

Lukas Thede, Stefan Winzeck, Zeynep Akata, Jonathan Richard Schwarz

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
17/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 17 of 20 reviewers recommend it
lenient 5/5
medium 8/10
strict 4/5
86%Must read
?Must readVote to see the score
NeurIPS 2026U VirginiaImperial College London & ThU California, BerkeleyLLM evaluation & benchmarks

Aligning Language Model Benchmarks with Pairwise Preferences

Reweighting benchmark items aligns static language model benchmarks with downstream pairwise preferences to rank unseen models, using as few as 20 well-chosen models.

Marco Gutierrez, Xinyi Leng, Hannah Chen, Jonathan Richard Schwarz and 2 more

Paris Poster Session 1, Wed, Dec 9, 12:30 PM–2:30 PM, Paris Poster Hall · Published 2026

– ReadersNo votes yet
14/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 14 of 20 reviewers recommend it
lenient 5/5
medium 7/10
strict 2/5