Papers by Kefan Li
The Pragmatic Mind of Machines: Tracing the Emergence of Pragmatic Competence in Large Language Models (2026.eacl-long)
Copied to clipboard
| Challenge: | Current large language models (LLMs) have demonstrated emerging capabilities in social intelligence tasks, including implicature resolution and theory-of-mind reasoning. |
| Approach: | They introduce a dataset grounded in the pragmatic concept of alternatives to evaluate whether large language models can accurately infer nuanced speaker intentions. |
| Outcome: | The proposed model can infer nuanced speaker intentions by inferring the speaker’s intended meaning and explaining when and why a speaker would choose one utterance over its alternative. |
Natural Language to Code Generation in Interactive Data Science Notebooks (2023.acl-long)
Copied to clipboard
Pengcheng Yin, Wen-Ding Li, Kefan Xiao, Abhishek Rao, Yeming Wen, Kensen Shi, Joshua Howland, Paige Bailey, Michele Catasta, Henryk Michalewski, Oleksandr Polozov, Charles Sutton
| Challenge: | Data scientists use computational notebooks to perform data wrangling and analytic tasks. |
| Approach: | They build a benchmark program that synthesizes programs given NL intents from users by using a Python code language model. |
| Outcome: | The proposed model outperforms public code LMs in a dataset of 1078 code generation problems using the pandas data analysis framework in data science notebooks. |
Efficient Test-Time Scaling via Temporal Reasoning Aggregation (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing dynamic early-exit methods rely on single-step confidence signals . existing approaches are unreliable for detecting reasoning convergence in multi-step settings . |
| Approach: | They propose a training-free framework for efficient test-time scaling that determines when to terminate reasoning based on temporal aggregation of multi-step evidence rather than instantaneous signals. |
| Outcome: | Experiments show that TRACE reduces reasoning token usage by 25% on average while maintaining accuracy within 1–2% of full-length reasoning. |