Xiang Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Xiang Li has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Yunshi Lan
East China Normal University Shanghai China
3 shared publications - Chao Yang
Shanghai Artificial Intelligence Laboratory
1 shared publication Chenrui Huang
Beijing Institute of Technology
1 shared publication- Hailong Gong
School of Mechanical Engineering, Beijing Institute of Technology, Beijing, China
1 shared publication - Hanyue Du
School of Data Science and Engineering, East China Normal University, Shanghai, China
1 shared publication Shaokun Yang
Beijing Institute of Technology
1 shared publication
Latest Publications
- Open Access
- 11 April 2025
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 39 (23) , 24485-24493
TreeEval: Benchmark-Free Evaluation of Large Language Models through Tree Planning
Recently, numerous new benchmarks have been established to evaluate the performance of large language models (LLMs) via either computing a holistic score or employing another LLM as a judge. However, these approaches suffer from data leakage due to the open access of the benchmark and inflexible evaluation process. To address this issue, we introduce TreeEval, a benchmark-free evaluation method for LLMs that let a high-performance LLM host an irreproducible evaluation session and essentially avoids the data leakage. Moreover, this LLM performs as an examiner to raise up a series of questions under a topic with a tree planing strategy, which considers the current evaluation status to decide the next question generation and ensures the completeness and efficiency of the evaluation process. We evaluate 6 models of different parameter sizes, including 7B, 13B, and 34B, and ultimately achieved the highest correlation coefficient with AlpacaEval2.0 using only around 45 questions. We also conduct more analysis to show the robustness and reliability of TreeEval.
- 11 April 2025
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 39 (23) , 24485-24493
Open AccessTreeEval: Benchmark-Free Evaluation of Large Language Models through Tree Planning
Recently, numerous new benchmarks have been established to evaluate the performance of large language models (LLMs) via either computing a holistic score or employing another LLM as a judge. However, these approaches suffer from data leakage due to the open access of the benchmark and inflexible evaluation process. To address this issue, we introduce TreeEval, a benchmark-free evaluation method for LLMs that let a high-performance LLM host an irreproducible evaluation session and essentially avoids the data leakage. Moreover, this LLM performs as an examiner to raise up a series of questions under a topic with a tree planing strategy, which considers the current evaluation status to decide the next question generation and ensures the completeness and efficiency of the evaluation process. We evaluate 6 models of different parameter sizes, including 7B, 13B, and 34B, and ultimately achieved the highest correlation coefficient with AlpacaEval2.0 using only around 45 questions. We also conduct more analysis to show the robustness and reliability of TreeEval.
- Open Access
- 26 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 4389-4400
Improving Zero-shot Visual Question Answering via Large Language Models with Reasoning Question Prompts
Zero-shot Visual Question Answering (VQA) is a prominent vision-language task that examines both the visual and textual understanding capability of systems in the absence of training data. Recently, by converting the images into captions, information across multi-modalities is bridged and Large Language Models (LLMs) can apply their strong zero-shot generalization capability to unseen questions. To design ideal prompts for solving VQA via LLMs, several studies have explored different strategies to select or generate question-answer pairs as the exemplar prompts, which guide LLMs to answer the current questions effectively. However, they totally ignore the role of question prompts. The original questions in VQA tasks usually encounter ellipses and ambiguity which require intermediate reasoning. To this end, we present Reasoning Question Prompts for VQA tasks, which can further activate the potential of LLMs in zero-shot scenarios. Specifically, for each question, we first generate self-contained questions as reasoning question prompts via an unsupervised question edition module considering sentence fluency, semantic integrity and syntactic invariance. Each reasoning question prompt clearly indicates the intent of the original question. This results in a set of candidate answers. Then, the candidate answers associated with their confidence scores acting as answer heuristics are fed into LLMs and produce the final answer. We evaluate reasoning question prompts on three VQA challenges, experimental results demonstrate that they can significantly improve the results of LLMs on zero-shot setting and outperform existing state-of-the-art zero-shot methods on three out of four data sets. Our source code is publicly released at https://github.com/ECNU-DASE-NLP/RQP.
- 26 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 4389-4400
Open AccessImproving Zero-shot Visual Question Answering via Large Language Models with Reasoning Question Prompts
Zero-shot Visual Question Answering (VQA) is a prominent vision-language task that examines both the visual and textual understanding capability of systems in the absence of training data. Recently, by converting the images into captions, information across multi-modalities is bridged and Large Language Models (LLMs) can apply their strong zero-shot generalization capability to unseen questions. To design ideal prompts for solving VQA via LLMs, several studies have explored different strategies to select or generate question-answer pairs as the exemplar prompts, which guide LLMs to answer the current questions effectively. However, they totally ignore the role of question prompts. The original questions in VQA tasks usually encounter ellipses and ambiguity which require intermediate reasoning. To this end, we present Reasoning Question Prompts for VQA tasks, which can further activate the potential of LLMs in zero-shot scenarios. Specifically, for each question, we first generate self-contained questions as reasoning question prompts via an unsupervised question edition module considering sentence fluency, semantic integrity and syntactic invariance. Each reasoning question prompt clearly indicates the intent of the original question. This results in a set of candidate answers. Then, the candidate answers associated with their confidence scores acting as answer heuristics are fed into LLMs and produce the final answer. We evaluate reasoning question prompts on three VQA challenges, experimental results demonstrate that they can significantly improve the results of LLMs on zero-shot setting and outperform existing state-of-the-art zero-shot methods on three out of four data sets. Our source code is publicly released at https://github.com/ECNU-DASE-NLP/RQP.
- 8 October 2023
- Published by Springer Nature
- p. 325-336
Towards Robust Chinese Spelling Check Systems: Multi-round Error Correction with Ensemble Enhancement
- 8 October 2023
- Published by Springer Nature
- p. 325-336
Towards Robust Chinese Spelling Check Systems: Multi-round Error Correction with Ensemble Enhancement
- 1 January 2022
- Published by Springer Nature
- p. 203-219
Real-Time Motion Planning and Control for a Formula Student Driverless Car
- 1 January 2022
- Published by Springer Nature
- p. 203-219
Real-Time Motion Planning and Control for a Formula Student Driverless Car