Papers by Dixuan Wang
Reason from Fallacy: Enhancing Large Language Models’ Logical Reasoning through Logical Fallacy Understanding (2024.findings-naacl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have demonstrated good performance in many reasoning tasks, but struggle with some more complex reasoning tasks including logical reasoning. |
| Approach: | They propose five concrete tasks from three cognitive dimensions of WHAT, WHY, and HOW to evaluate LLMs’ capability of logical fallacy understanding. |
| Outcome: | The proposed dataset can be used to evaluate LLMs’ LFU capability and to fine-tune LLM models to obtain significantly enhanced performance on logical reasoning. |
Benchmarking Language Model Creativity: A Case Study on Code Generation (2025.naacl-long)
Copied to clipboard
| Challenge: | Recent studies on LLM creativity evaluation focus on open-ended generation tasks . however, the degree to which LLMs possess and utilize creativity for problem-solving remains unclear . |
| Approach: | They propose a framework for quantifying LLM creativity that incorporates design ingredients . they introduce DENIAL PROMPTING which pushes LLMs to develop more creative solutions . |
| Outcome: | The proposed framework quantifies creativity in LLMs on Codeforces problems . it also finds that even the most creative model fails to demonstrate human-like creativity . |
ToNER: Type-oriented Named Entity Recognition with Generative Language Model (2024.lrec-main)
Copied to clipboard
| Challenge: | Input too many potential entity types would distract the model inevitably. |
| Approach: | They propose to use a generative model to exploit entity types' merit on promoting NER task by appending a type matching model to identify the entity types most likely to appear in the sentence. |
| Outcome: | The proposed framework exploits entity types' merit on promoting NER task by adding auxiliary task to the model to discover the entity types. |