Papers by Dayang Li
What’s Left Unsaid? Detecting and Correcting Misleading Omissions in Multimodal News Previews (2026.acl-long)
Copied to clipboard
| Challenge: | Existing efforts to detect factually incorrect content are omitted by creators who subtly reshape impressions by omitting crucial background context. |
| Approach: | They propose a multi-stage pipeline that simulates preview-based and context-based understanding and a OMGuard pipeline that combines interpretation-aware fine-tuning and rationale-guided misleading content correction. |
| Outcome: | The proposed framework lifts an 8B model’s detection accuracy to the level of a 235B LVLM while delivering stronger end-to-end correction. |
Correct When Paired, Wrong When Split: Decoupling and Editing Modality-Specific Neurons in MLLMs (2026.acl-long)
Copied to clipboard
Tingchao Fu, Wenkai Wang, Fanxiao Li, Huadong Zhang, Jinhong Zhang, Dayang Li, Yunyun Dong, Renyang Liu, Wei Zhou
| Challenge: | Existing knowledge editing paradigms suffer from editing decoupling failures . entity knowledge is sequestered into disentangled modality-specific pathways . |
| Approach: | They propose a method that explicitly disentangles and localizes modality-specific neuron groups for targeted knowledge. |
| Outcome: | The proposed method outperforms baselines in reliability and consistency while preserving model locality. |
IMRRF: Integrating Multi-Source Retrieval and Redundancy Filtering for LLM-based Fake News Detection (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing methods to detect fake news rely on manual checking, which is time-consuming. |
| Approach: | They propose a model which integrates textual corpus retrieval with knowledge graph retrieval to retrieve more comprehensive evidence and a redundant information filtering strategy which minimizes the influence of irrelevant information on the LLM reasoning process. |
| Outcome: | The proposed method outperforms state-of-the-art fact-checking baselines on two challenging fact- checking datasets. |