AI ethics evidence index Search
Source-linked daily record
Evidence record 425 · automatically gathered

ADAPT: Attention Dynamics Alignment with Preference Tuning for Faithful MLLMs

Multimodal Large Language Models (MLLMs) are critically hampered by hallucination, generating content inconsistent with the provided image. In this paper, we identify an internal signature of hallucination: progressive degradation of text-to-image cross-attention during generation, leading to specific failure patterns like unfocused or biased attention. Existing mitigation strategies are largely outcome-driven and do not explicitly target this failure mode. To address this problem, we propose AD

Record details

Published: 30 June 2026
Source: arXiv
Category: Research
Topics: Bias & fairness · Safety & alignment
Retrieved: 14 July 2026

source-onlyevidence status

These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.

Shared topic: Bias & fairness · Shared topic: Safety & alignment

Efficient bias mitigation in T2I diffusion models using Concept Graphs

arXiv · 3 July 2026

Shared topic: Bias & fairness · Shared topic: Safety & alignment

Integrated Altruistic and Fairness Preference Induces Advanced Mutual Cooperation in Sequential Social Dilemmas

arXiv · 6 July 2026

Shared topic: Bias & fairness · Shared topic: Safety & alignment

MMed-Bench-IR: A Heterogeneous Benchmark for Multilingual Medical Information Retrieval

arXiv · 23 June 2026

Shared topic: Bias & fairness · Shared topic: Safety & alignment

X-FEMR: A Token-level Explainable Approach for Electronic Health Records Foundation Models using Transformer-based Models

arXiv · 7 July 2026

Shared topic: Bias & fairness · Shared topic: Safety & alignment

Affective AI Safety: The Missing Piece in LLM Safety

arXiv · 22 June 2026

Shared topic: Bias & fairness · Shared topic: Safety & alignment

Trustworthy Machine Learning through the Lens of Combinatorial Optimization: Survey and Research Perspectives

arXiv fairness query · 8 July 2026

How to cite this record

ethics.ai (30 June 2026), “ADAPT: Attention Dynamics Alignment with Preference Tuning for Faithful MLLMs,” evidence record 425, https://ethics.ai/record/425 (originally published by arXiv).

JSON

Use and limitations

This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.