Papers by Feifan Yang
Two Pathways to Truthfulness: On the Intrinsic Encoding of LLM Hallucinations (2026.acl-long)
Copied to clipboard
Wen Luo, Guangyue Peng, Wei Li, Shaohang Wei, Feifan Song, Liang Wang, Nan Yang, Xingxing Zhang, Jing Jin, Furu Wei, Houfeng Wang
| Challenge: | Previous work shows that large language models generate hallucinations, yet the origins and mechanisms of these signals remain unclear. |
| Approach: | They propose to validate and disentangle two different pathways for truthfulness cues . they also propose to use the same mechanism to derive self-contained evidence from the generated answer . |
| Outcome: | The proposed applications improve hallucination detection performance by integrating two different inputs. |
Psycholinguistic Tripartite Graph Network for Personality Detection (2021.acl-long)
Copied to clipboard
| Challenge: | Existing work on personality detection from online posts adopts multifarious deep neural networks to represent the posts and builds predictive models in a data-driven manner without the exploitation of psycholinguistic knowledge. |
| Approach: | They propose a psycholinguistic knowledge-based tripartite graph network, TrigNet, which consists of a tripartitic graph network and a BERT-based graph initializer. |
| Outcome: | The proposed graph network outperforms the existing state-of-the-art model by 3.47 and 2.10 points in average F1 on two datasets. |
Learning to Answer Psychological Questionnaire for Personality Detection (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing text-based personality detection research relies on data-driven approaches to implicitly capture personality cues in online posts lacking the guidance of psychological knowledge. |
| Approach: | They propose a model to capture key information in texts and a questionnaire to help the user to make a personality assessment. |
| Outcome: | The proposed model captures key information in texts and a questionnaire and can be used to improve personality prediction. |