Papers by Eugene Yang
CLERC: A Dataset for U. S. Legal Case Retrieval and Retrieval-Augmented Analysis Generation (2025.findings-naacl)
Copied to clipboard
Abe Bohan Hou, Orion Weller, Guanghui Qin, Eugene Yang, Dawn Lawrie, Nils Holzenberger, Andrew Blair-Stanek, Benjamin Van Durme
| Challenge: | a dataset of case law is used to train and evaluate models for writing legal analyses . current approaches struggle to find relevant cases and generate legal analyses, authors say . |
| Approach: | They build a dataset of case law to support information retrieval and retrieval-augmented generation. |
| Outcome: | The proposed dataset supports two important backbone tasks: retrieval (IR) and retrieval-augmented generation (RAG). |
Generating Negative Samples by Manipulating Golden Responses for Unsupervised Learning of a Response Evaluation Model (2021.naacl-main)
Copied to clipboard
| Challenge: | Existing metrics that rely on comparisons to a set of known correct responses do not account for the variety of responses and therefore correlate poorly with human judgment. |
| Approach: | They propose a method of manipulating a golden response to create a new negative response that is designed to be inappropriate within the context while maintaining high similarity with the original golden response. |
| Outcome: | The proposed model can be made using unsupervised learning for the next-utterance prediction task on English datasets and shows that using the negative samples alongside random negative samples can increase the model’s correlation with human evaluations. |
WikiVideo: Article Generation from Multiple Videos (2026.findings-acl)
Copied to clipboard
Alexander Martin, Reno Kriz, William Gantt Walden, Kate Sanders, Hannah Recknor, Eugene Yang, Francis Ferraro, Benjamin Van Durme
| Challenge: | Existing methods for retrieval-augmented generation focus on text rather than video. |
| Approach: | They propose a benchmark to generate Wikipedia-style articles from multiple videos . they propose 'collaborative article generation' that leverages an r1-style reasoning model and a VideoLLM to draw higher-level inferences about the target event than is possible with VideoLLms alone. |
| Outcome: | The proposed method outperforms existing methods in oracle retrieval and RAG settings while suggesting promising avenues for future work. |