Lechen Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Lechen Zhang has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Lu Wang
Shenzhen University
3 shared publications - Bangzhao Shu
University of Michigan Ann Arbor MI USA
2 shared publications Dallas Card
University of Michigan Ann Arbor MI USA
2 shared publications- David Jurgens
University of Michigan University of Michigan
2 shared publications Lajanugen Logeswaran
LG AI Research Ann Arbor MI USA
2 shared publications- Lavinia Dunagan
University of Michigan Ann Arbor MI USA
2 shared publications
Latest Publications
- Open Access
Skill-Aware Data Selection and Fine-Tuning for Data-Efficient Reasoning Distillation
Large reasoning models such as DeepSeek-R1 and their distilled variants achieve strong performance on complex reasoning tasks. Yet, distilling these models often demands large-scale data for supervised fine-tuning (SFT), motivating the pursuit of data-efficient training methods. To address this, we propose a skill-centric distillation framework that efficiently transfers reasoning ability to weaker models with two components: (1) Skill-based data selection, which prioritizes examples targeting the student model's weaker skills, and (2) Skill-aware fine-tuning, which encourages explicit skill decomposition during problem solving. With only 1,000 training examples selected from a 100K teacher-generated corpus, our method surpasses random SFT baselines by +1.6% on Qwen3-4B and +1.4% on Qwen3-8B across five mathematical reasoning benchmarks. Further analysis confirms that these gains concentrate on skills emphasized during training, highlighting the effectiveness of skill-centric training for efficient reasoning distillation.
Open AccessSkill-Aware Data Selection and Fine-Tuning for Data-Efficient Reasoning Distillation
Large reasoning models such as DeepSeek-R1 and their distilled variants achieve strong performance on complex reasoning tasks. Yet, distilling these models often demands large-scale data for supervised fine-tuning (SFT), motivating the pursuit of data-efficient training methods. To address this, we propose a skill-centric distillation framework that efficiently transfers reasoning ability to weaker models with two components: (1) Skill-based data selection, which prioritizes examples targeting the student model's weaker skills, and (2) Skill-aware fine-tuning, which encourages explicit skill decomposition during problem solving. With only 1,000 training examples selected from a 100K teacher-generated corpus, our method surpasses random SFT baselines by +1.6% on Qwen3-4B and +1.4% on Qwen3-8B across five mathematical reasoning benchmarks. Further analysis confirms that these gains concentrate on skills emphasized during training, highlighting the effectiveness of skill-centric training for efficient reasoning distillation.
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 17919-17936
VeriFact: Enhancing Long-Form Factuality Evaluation with Refined Fact Extraction and Reference Facts
Xin Liu, Lechen Zhang, Sheza Munir, Yiyang Gu, Lu Wang. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 17919-17936
Open AccessVeriFact: Enhancing Long-Form Factuality Evaluation with Refined Fact Extraction and Reference Facts
Xin Liu, Lechen Zhang, Sheza Munir, Yiyang Gu, Lu Wang. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.
- Top Cited PapersOpen Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 33090-33110
FactBench: A Dynamic Benchmark for In-the-Wild Language Model Factuality Evaluation
Farima Fatahi Bayat, Lechen Zhang, Sheza Munir, Lu Wang. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 33090-33110
Top Cited PapersOpen AccessFactBench: A Dynamic Benchmark for In-the-Wild Language Model Factuality Evaluation
Farima Fatahi Bayat, Lechen Zhang, Sheza Munir, Lu Wang. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.
- Open Access
You don't need a personality test to know these models are unreliable: Assessing the Reliability of Large Language Models on Psychometric Instruments
The versatility of Large Language Models (LLMs) on natural language understanding tasks has made them popular for research in social sciences. To properly understand the properties and innate personas of LLMs, researchers have performed studies that involve using prompts in the form of questions that ask LLMs about particular opinions. In this study, we take a cautionary step back and examine whether the current format of prompting LLMs elicits responses in a consistent and robust manner. We first construct a dataset that contains 693 questions encompassing 39 different instruments of persona measurement on 115 persona axes. Additionally, we design a set of prompts containing minor variations and examine LLMs' capabilities to generate answers, as well as prompt variations to examine their consistency with respect to content-level variations such as switching the order of response options or negating the statement. Our experiments on 17 different LLMs reveal that even simple perturbations significantly downgrade a model's question-answering ability, and that most LLMs have low negation consistency. Our results suggest that the currently widespread practice of prompting is insufficient to accurately and reliably capture model perceptions, and we therefore discuss potential alternatives to improve these issues.
Open AccessYou don't need a personality test to know these models are unreliable: Assessing the Reliability of Large Language Models on Psychometric Instruments
The versatility of Large Language Models (LLMs) on natural language understanding tasks has made them popular for research in social sciences. To properly understand the properties and innate personas of LLMs, researchers have performed studies that involve using prompts in the form of questions that ask LLMs about particular opinions. In this study, we take a cautionary step back and examine whether the current format of prompting LLMs elicits responses in a consistent and robust manner. We first construct a dataset that contains 693 questions encompassing 39 different instruments of persona measurement on 115 persona axes. Additionally, we design a set of prompts containing minor variations and examine LLMs' capabilities to generate answers, as well as prompt variations to examine their consistency with respect to content-level variations such as switching the order of response options or negating the statement. Our experiments on 17 different LLMs reveal that even simple perturbations significantly downgrade a model's question-answering ability, and that most LLMs have low negation consistency. Our results suggest that the currently widespread practice of prompting is insufficient to accurately and reliably capture model perceptions, and we therefore discuss potential alternatives to improve these issues.
- Top Cited PapersOpen Access
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 5263-5281
You don’t need a personality test to know these models are unreliable: Assessing the Reliability of Large Language Models on Psychometric Instruments
Bangzhao Shu, Lechen Zhang, Minje Choi, Lavinia Dunagan, Lajanugen Logeswaran, Moontae Lee, Dallas Card, David Jurgens. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2024.
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 5263-5281
Top Cited PapersOpen AccessYou don’t need a personality test to know these models are unreliable: Assessing the Reliability of Large Language Models on Psychometric Instruments
Bangzhao Shu, Lechen Zhang, Minje Choi, Lavinia Dunagan, Lajanugen Logeswaran, Moontae Lee, Dallas Card, David Jurgens. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2024.