arXiv (All)
open access
MLLMs Hallucinate when Information Distribution Drifts in Synergy Heads
Multimodal Large Language Models (MLLMs) often struggle with hallucinations, thus hindering their reliable practical applications. Existing attention-based mitigation methods mainly rely on indirect signals (e.g., attention weights) that fail to accurately reflect the actual information shift underl
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- The auditory trap: early semantic conflict and late monitoring breakdown drive false memories in cognitive aging.#378355
- Effects of bimodal divided attention on cortical representations of linguistic context during continuous speech perception in noise#241458
- Decoupling Internal Representational Changes and Causal Importance in Fine-Tuned Large Language Models#1035083
- Directional Hallucinations: Ideological Drift in News-Grounded LLM Question Answering#1014773
- Modality-Independent Core Brain Network for Language as Proved by Sign Language#1159820
Record · ID 1013209
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive