Tianhe Lin — accepted AI-conference papers

2025

Implicit Reasoning in Transformers is Reasoning through Shortcuts

Tianhe Lin, Jian Xie, Siyu Yuan, Deqing Yang

ACL 2025finding

Test-time compute is emerging as a new paradigm for enhancing language models’ complex multi-step reasoning capabilities, as demonstrated by the success of OpenAI’s o1 and o3, as well as DeepSeek’s R1. Compared to explicit reasoning in test-time compute, implicit reasoning is more inference-efficien…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2024

Evaluating Character Understanding of Large Language Models via Character Profiling from Fictional Works

Xinfeng Yuan, Siyu Yuan, Yuhan Cui, Tianhe Lin, Xintao Wang, Rui Xu +2

EMNLP 2024main

Large language models (LLMs) have demonstrated impressive performance and spurred numerous AI applications, in which role-playing agents (RPAs) are particularly popular, especially for fictional characters. The prerequisite for these RPAs lies in the capability of LLMs to understand characters from…

Cited by 17 Source ↗PDF ↗code ↗Scholar ↗