Papers by Wei-Fan Chen
Explainable Hallucination through Natural Language Inference Mapping (2025.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) often generate hallucinated content, making it crucial to identify and quantify inconsistencies in their outputs. |
| Approach: | They propose a framework that maps entailment and contradiction relations between inputs and outputs using a natural language inference model. |
| Outcome: | The proposed framework outperforms state-of-the-art methods by five percentage points while providing clear, interpretable explanations. |
Detecting Media Bias in News Articles using Gaussian Bias Distributions (2020.findings-emnlp)
Copied to clipboard
| Challenge: | a new study shows that media bias is not only about honesty or accuracy, but also about taste or preference. |
| Approach: | They propose to use second-order information to detect media bias in articles . they propose to analyze the frequency, positions, and sequential order of biased statements . |
| Outcome: | The proposed model outperforms other models that use second-order information on biased statements on an existing media bias dataset. |
Controlled Neural Sentence-Level Reframing of News Articles (2021.findings-emnlp)
Copied to clipboard
| Challenge: | a news article is framed from a specific perspective, but reframing can be difficult . a framed article can be used to communicate with opposing camps of audiences . |
| Approach: | They propose to reframe news articles using a media frame corpus to achieve this . they propose three strategies to train neural models for reframing . |
| Outcome: | The proposed techniques maintain coherence of sentences and reframe them correctly . the proposed techniques are effective but have tradeoffs . |
Unraveling the Search Space of Abusive Language in Wikipedia with Dynamic Lexicon Acquisition (D19-50)
Copied to clipboard
| Challenge: | Existing methods to detect abusive language only train one classifier for the whole variety of offending . a new method can support a moderator with explicit unraveled explanations for why something was flagged as abusive . |
| Approach: | a new method is proposed to distinguish explicitly abusive cases from the more "shadowed" ones . the researchers extend a lexicon of abusive terms to include new obfuscations of abusive words . |
| Outcome: | a new method can distinguish explicitly abusive cases from the more "shadowed" ones . the method can support a moderator with explicit unraveled explanations for why something was flagged as abusive . |
Reference-guided Style-Consistent Content Transfer (2024.lrec-main)
Copied to clipboard
| Challenge: | Text style transfer involves changing the style of a text while preserving its original style. |
| Approach: | They propose a task of style-consistent content transfer which involves modifying a text’s content based on a provided reference statement while preserving its original style. |
| Outcome: | The proposed approach meets three important conditions: reference faithfulness, style adherence, and coherence. |
Belief-based Generation of Argumentative Claims (2021.eacl-main)
Copied to clipboard
| Challenge: | Existing methods to generate argument with the ability to encode beliefs are limited by the noise generated by the automatic collection of bag-of-words. |
| Approach: | They propose to augment argument generation technology with ability to encode beliefs . they model users' beliefs via their stances on big issues and extend text generation models with extra input reflecting user's beliefs. |
| Outcome: | The proposed approach is low in effectiveness because of the noise produced by the automatic collection of bag-of-words. |