Papers by Yisong Miao
Discursive Socratic Questioning: Evaluating the Faithfulness of Language Models’ Understanding of Discourse Relations (2024.acl-long)
Copied to clipboard
| Challenge: | Discursive Socratic Questioning (DISQ) assesses a model's understanding of discourse relations by requiring systematic accuracy over multiple questions. |
| Approach: | They propose a method that evaluates faithfulness of understanding discourse based on question answering. |
| Outcome: | The proposed method evaluates the faithfulness of understanding discourse based on question answering. |
The ELCo Dataset: Bridging Emoji and Lexical Composition (2024.lrec-main)
Copied to clipboard
| Challenge: | Emoji-Lexical Composition dataset provides parallel annotations of emoji sequences corresponding to English phrases. |
| Approach: | They propose a dataset that offers parallel annotations of emoji sequences corresponding to English phrases. |
| Outcome: | The Emoji-Lexical Composition (ELCo) dataset offers parallel annotations of emoji sequences corresponding to English phrases. |
Discursive Circuits: How Do Language Models Understand Discourse Relations? (2025.emnlp-main)
Copied to clipboard
| Challenge: | Discourse structure is essential for ensuring language models behave safely and ethically. |
| Approach: | They propose a task where a model completes a discourse given a specified relation . they propose CUDR task that enables activation patching to make circuit discovery feasible . |
| Outcome: | The proposed model recovers discourse understanding in the English PDTB-based CuDR task. |