Good Papers

Showing papers from New York University Shanghai Show all papers

80%Must read
?Must readVote to see the score
arXivNew York University ShanghaiMechanistic interpretability

Making LLMs Say What They Think: Measuring and Improving CoT-Interpretability Alignment

We introduce CIA to measure chain-of-thought alignment with internal reasoning, finding low alignment that post-training improves substantially while maintaining accuracy.

Yihuai Hong, Shauli Ravfogel, Chen Zhao, Eunsol Choi

Published Sep 30, 2026 · 0 citations · ▲ 2 on Hugging Face · Code ★ 1

– ReadersNo votes yet
12/20 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: 12 of 20 reviewers recommend it
lenient 5/5
medium 7/10
strict 0/5
89%Must read
?Must readVote to see the score
NeurIPS 2026New YorkNewYorkInstitute of Computing TechnologNous ResearchModalTest-time compute

Multi-Token Residual Prediction

Multi-token Residual Prediction predicts next-step residuals via hidden states to denoise more tokens per pass, accelerating diffusion language models up to 1.4x or recovering up to 22.6 accuracy points on HumanEval.

Yufeng Xu, Zishuo Bao, Qian Wang, Zeshen Zhang and 5 more

Atlanta Poster Session 3, Thu, Dec 10, 10:00 AM–1:00 PM, Hall C1 · Published 2026

– ReadersNo votes yet
16/20 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: 16 of 20 reviewers recommend it
lenient 5/5
medium 10/10
strict 1/5