Author name cluster

Hailin Chen

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

3 papers

2 author rows

TMLR Journal 2025 Journal Article

A Comprehensive Survey of Contamination Detection Methods in Large Language Models

Mathieu Ravaut
Bosheng Ding
Fangkai Jiao
Hailin Chen
Xingxuan Li
Ruochen Zhao
Chengwei Qin
Caiming Xiong

With the rise of Large Language Models (LLMs) in recent years, abundant new opportunities are emerging, but also new challenges, among which contamination is quickly becoming critical. Business applications and fundraising in Artificial Intelligence (AI) have reached a scale at which a few percentage points gained on popular question-answering benchmarks could translate into dozens of millions of dollars, placing high pressure on model integrity. At the same time, it is becoming harder and harder to keep track of the data that LLMs have seen; if not impossible with closed-source models like GPT-4 and Claude-3 not divulging any information on the training set. As a result, contamination becomes a major issue: LLMs’ performance may not be reliable anymore, as the high performance may be at least partly due to their previous exposure to the data. This limitation jeopardizes real capability improvement in the field of NLP, yet, there remains a lack of methods on how to efficiently detect contamination. In this paper, we survey all recent work on contamination detection with LLMs, analyzing their methodologies and use cases to shed light on the appropriate usage of contamination detection methods. Our work calls the NLP research community’s attention into systematically taking into account contamination bias in LLM evaluation.

PDF Details

JBHI Journal 2025 Journal Article

GATPDD: an Enhanced Deep Learning Framework for Predicting Drug-Parasitic Disease Associations

Hailin Chen
Zhongling Li

Parasitic diseases pose a significant threat to human health. Accurate and robust prediction of drug-parasitic disease associations is critical to advancing drug discovery and developing parasitic disease therapies. However, biomedical data in this field is often too scarce to train a generalized machine learning model. Although computational methods have been developed for predicting potential drug-parasitic disease associations, their performances were restricted owing to data limitation. Here we propose a deep learning framework entitled GATPDD for improving drug-parasitic disease association predictions. Our model integrates enhanced Deep Graph Infomax with multi-head Graph Attention Networks and Neighborhood Interaction Attention to refine feature learning and embedding aggregation in the scenario of limited benchmark datasets. Extensive comparative experiments demonstrate that GATPDD effectively alleviates the data scarcity problem for the model generalization and significantly improves accuracy and robustness over state-of-the-art methods. We further use GATPDD to conduct case studies and results validate its ability to identify reliable drug-parasitic disease associations in real-world applications, suggesting the potential of GATPDD in drug discovery for parasitic disease therapies.

Details DOI

ICLR Conference 2024 Conference Paper

CodeChain: Towards Modular Code Generation Through Chain of Self-revisions with Representative Sub-modules

Hung Le 0003
Hailin Chen
Amrita Saha
Akash Gokul
Doyen Sahoo
Shafiq Joty

Large Language Models (LLMs) have already become quite proficient at solving simpler programming tasks like those in HumanEval or MBPP benchmarks. However, solving more complex and competitive programming tasks is still quite challenging for these models - possibly due to their tendency to generate solutions as monolithic code blocks instead of decomposing them into logical sub-tasks and sub-modules. On the other hand, experienced programmers instinctively write modularized code with abstraction for solving complex tasks, often reusing previously developed modules. To address this gap, we propose CodeChain, a novel framework for inference that elicits modularized code generation through a chain of self-revisions, each being guided by some representative sub-modules generated in previous iterations. Concretely, CodeChain first instructs the LLM to generate modularized codes through chain-of-thought prompting. Then it applies a chain of self-revisions by iterating the two steps: 1) extracting and clustering the generated sub-modules and selecting the cluster representatives as the more generic and re-usable implementations, and 2) augmenting the original chain-of-thought prompt with these selected module-implementations and instructing the LLM to re-generate new modularized solutions. We find that by naturally encouraging the LLM to reuse the previously developed and verified sub-modules, CodeChain can significantly boost both modularity as well as correctness of the generated solutions, achieving relative pass@1 improvements of 35\% on APPS and 76\% on CodeContests. It is shown to be effective on both OpenAI LLMs as well as open-sourced LLMs like WizardCoder. We also conduct comprehensive ablation studies with different methods of prompting, number of clusters, model sizes, program qualities, etc., to provide useful insights that underpin CodeChain's success.

Details