Good Papers

Showing Behavior & reasoning editing Show all papers

76%Highly rated
?Highly ratedVote to see the score
ICLRU VirginiaAT&TFlorida StateBehavior & reasoning editing

Reforming the Mechanism: Editing Reasoning Patterns in LLMs with Circuit Reshaping

REdit reshapes LLM neural circuits before editing to reduce reasoning-pattern interference, improving generality and locality over broad training baselines.

Zhenyu Lei, Qiong Wu, Jianxiong Dong, Yinhan He and 3 more

Published Jan 25, 2026 · 0 citations

– ReadersNo votes yet
10/20 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: 10 of 20 reviewers recommend it
lenient 4/5
medium 6/10
strict 0/5
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026Northwestern PolytechnicalNorthwest Polytechnical UniversiBehavior & reasoning editing

PACE: Partial-state Amortized Constraint Editing for Neural Combinatorial Optimization

Bohao Li, Chenhao Yuan, Ying Li, Pei He and 1 more

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
0/20 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: 0 of 20 reviewers recommend it
lenient 0/5
medium 0/10
strict 0/5
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026Eon Systems PBCBehavior & reasoning editing

MapShift: Controlled Post-Intervention Evaluation for Embodied World Models

Aarav Sinha

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
0/20 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: 0 of 20 reviewers recommend it
lenient 0/5
medium 0/10
strict 0/5
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026Chinese University of Hong KongBehavior & reasoning editing

Refinement as a Service: Algorithmic Predictor Refinement

Wei Tang, Hanrui Zhang

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
0/20 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: 0 of 20 reviewers recommend it
lenient 0/5
medium 0/10
strict 0/5
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026U MelbourneIBM ResearchBehavior & reasoning editing

Understanding Model Reprogramming: A Reachability and Relabeling Perspective

Zesheng Ye, Pin-Yu Chen, Feng Liu

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
0/20 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: 0 of 20 reviewers recommend it
lenient 0/5
medium 0/10
strict 0/5
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026AaltoELLIS Institute Finland AaltoBehavior & reasoning editing

Constrained Look-ahead Guidance for Interference-Aware Flow Editing

Doudou ZHANG, Qi CHEN

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

– ReadersNo votes yet
0/20 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: 0 of 20 reviewers recommend it
lenient 0/5
medium 0/10
strict 0/5
83%Must read
?Must readVote to see the score
NeurIPS 2026UCSDUC San DiegoU California, San DiegoBehavior & reasoning editing

Steer2Edit: From Activation Steering to Component-Level Editing

Steer2Edit converts inference-time activation steering into training-free, component-level rank-1 weight edits that improve safety, truthfulness, and reasoning efficiency over global interventions.

Chung-En Sun, Ge Yan, Zimo Wang, Lily Weng

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · ▲ 1 on Hugging Face

– ReadersNo votes yet
13/20 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: 13 of 20 reviewers recommend it
lenient 5/5
medium 8/10
strict 0/5
91%Must read
?Must readVote to see the score
NeurIPS 2026Michigan StateGoogleHippocratic AIU GeorgiaBehavior & reasoning editing

Crafting Reversible SFT Behaviors in Large Language Models

LCDD constructs sparse, causally necessary subnetworks for SFT behaviors, and SFT-Eraser reverses them via activation-matched soft prompts without weight changes.

Yuping Lin, Pengfei He, Yue XING, Yingqian Cui and 4 more

Atlanta Poster Session 1, Wed, Dec 9, 10:00 AM–1:00 PM, Hall C1 · 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 9/10
strict 3/5
86%Must read
?Must readVote to see the score
NeurIPS 2026TelePIXTelepixBehavior & reasoning editing

Platonic Task Arithmetic

Universal Task Descriptors represent tasks as architecture-independent matrices to enable cross-model arithmetic, retaining 74, 80% of within-model gains across six families.

Junghwan Park, Woojin Cho

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · 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 3/5
medium 8/10
strict 3/5
83%Must read
?Must readVote to see the score
NeurIPS 2026U Texas at San AntonioU Texas, San AntonioBehavior & reasoning editing

Residual Paving: Diagnosing the Routing Bottleneck in Selective Refusal Editing

Residual Paving separates routing selectivity from edit capacity in selective refusal editing, reducing edit refusal to 4.0% and identifying route selectivity as the main bottleneck.

Bryce Hinkley, Peyman Najafirad

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
13/20 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: 13 of 20 reviewers recommend it
lenient 3/5
medium 7/10
strict 3/5