AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

DARE to Mitigate Hallucination: Dual-path Auto-Regressive-aware Editing

Jaeho Lee, Jeongeun Lee, Gyeong-Moon Park

ECCV 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Preference tuning against hallucination · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add AR-aware editing to TF editing (ablation)DARE (LLaVA-1.5) · CHAIRCHAIR_S: 20.53 -> 15.83Improved
add visual-difference editing to AR editing (ablation)DARE (LLaVA-1.5) · CHAIRCHAIR_S: 17.61 -> 15.57Improved
add visual-difference editing to TF editing (ablation)DARE (LLaVA-1.5) · CHAIRCHAIR_S: 20.53 -> 17.17Improved
add AR editing to TF+visual-difference editing (full DARE) (ablation)DARE (LLaVA-1.5) · CHAIRCHAIR_S: 17.17 -> 14.93Improved
add TF editing to AR+visual-difference editing (full DARE) (ablation)DARE (LLaVA-1.5) · CHAIRCHAIR_S: 15.57 -> 14.93Improved
add visual-difference editing to TF+AR editing (full DARE) (ablation)DARE (LLaVA-1.5) · CHAIRCHAIR_I: 6.47 -> 6.07Improved
AR-aware editing alone vs TF-based editing alone (ablation)LLaVA-1.5 · CHAIRCHAIR_S: 20.53 -> 17.61Improved
edit layers 16-31 instead of 0-15 (ablation)AR-aware editing (LLaVA-1.5) · CHAIRCHAIR_S: 17.70 -> 15.11Improved
edit layers 16-31 instead of 24-31 (ablation)AR-aware editing (LLaVA-1.5) · CHAIRCHAIR_S: 16.87 -> 15.11Improved
HalluSpace rank k=2 instead of k=8 (ablation)AR-aware editing (LLaVA-1.5) · CHAIRCHAIR_S: 17.09 -> 15.11Improved
HalluSpace rank k=2 instead of k=1 (ablation)AR-aware editing (LLaVA-1.5) · CHAIRCHAIR_S: 18.44 -> 15.11Improved
temporal window 3 instead of 1 (ablation)AR-aware editing (LLaVA-1.5) · CHAIRCHAIR_S: 16.92 -> 15.11Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy