Papers by Xudong Han

22 papers
FairLib: A Unified Framework for Assessing and Improving Fairness (2022.emnlp-demos)

Copied to clipboard

Challenge: Existing approaches to assess and improve model fairness have been inconsistent and inconsistent.
Approach: They propose an open-source python library for assessing and improving model fairness.
Outcome: The proposed framework can be used for natural language, images, and audio.
Evaluating Debiasing Techniques for Intersectional Biases (2021.emnlp-main)

Copied to clipboard

Challenge: Existing methods for debiasing protected attributes have been limited to binary attributes in isolation, however many corpora involve multiple such attributes, possibly with higher cardinality.
Approach: They propose to evaluate a bias-constrained model which is new to NLP and an extension of the iterative nullspace projection technique which can handle multiple identities.
Outcome: The proposed model is based on a new iterative nullspace projection technique which can handle multiple identities.
A Chinese Dataset for Evaluating the Safeguards in Large Language Models (2024.findings-acl)

Copied to clipboard

Challenge: a recent study has shown that large language models can produce harmful responses, exposing users to unexpected risks.
Approach: They propose a dataset for the safety evaluation of Chinese LLMs in Mandarin Chinese . they extend the dataset to better identify false negative and false positive examples .
Outcome: The proposed dataset is for the safety evaluation of Chinese LLMs, and is based on a Chinese dataset.
Optimising Equal Opportunity Fairness in Model Training (2022.naacl-main)

Copied to clipboard

Challenge: Existing methods to reduce bias have been shown to be effective over real-world datasets.
Approach: They propose two new training objectives which directly optimise for the widely-used criterion of equal opportunity.
Outcome: The proposed training objectives directly optimise for the widely-used criterion of equal opportunity while maintaining high performance over two classification tasks.
Weakly-Supervised Temporal Article Grounding (2022.emnlp-main)

Copied to clipboard

Challenge: Existing VG models make unrealistic assumptions about how to ground video segments . a recent study has shown that video grounding can be useful for downstream applications .
Approach: They propose a new task: Weakly-Supervised temporal Article Grounding (WSAG) given an article and a relevant video, WSAG aims to localize all "groundable" sentences to the video.
Outcome: The proposed method is simple but effective, and it can be used in real-world applications.
Loki: An Open-Source Tool for Fact Verification (2025.coling-demos)

Copied to clipboard

Challenge: Loki is an open-source fact-checking tool designed to address the growing problem of misinformation.
Approach: They propose a tool that breaks down the fact-checking task into five steps . they propose LOKI, which offers a semiautomated, human-in-the-loop approach .
Outcome: a new open-source tool is designed to address the growing problem of misinformation . the tool breaks down the fact-checking task into five steps to assist human judgment .
Balancing out Bias: Achieving Fairness Through Balanced Training (2022.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to reducing group bias do not account for correlations between author demographics and linguistic variables, limiting their effectiveness.
Approach: They extend a method for countering group bias using balanced training by balancing each demographic group in training and using protected attributes as input.
Outcome: The proposed model outperforms all other methods when combined with balanced training.
RESIN: A Dockerized Schema-Guided Cross-document Cross-lingual Cross-media Information Extraction and Event Tracking System (2021.naacl-demos)

Copied to clipboard

Challenge: We present a new information extraction system that can construct temporal event graphs from news documents.
Approach: They propose a temporal event graph extraction system that can extract news documents . they extend the system from sentence-level event extraction to cross-document cross-media event extraction .
Outcome: The proposed system can extract temporal event graphs from news documents in multiple languages and multiple data modalities.
Stealthy Jailbreak Attacks on Large Language Models via Benign Data Mirroring (2025.naacl-long)

Copied to clipboard

Challenge: Existing black-box jailbreak methods often rely on model feedback . existing methods may be intercepted by content moderators during the search process .
Approach: They propose a method that guides malicious prompt construction by local training a mirror model of the target black-box model through benign data distillation.
Outcome: The proposed method achieves a 92% attack success rate and 80% stealth rate on a subset of AdvBench.
SCALAR: Scientific Citation-based Live Assessment of Long-context Academic Reasoning (2026.eacl-long)

Copied to clipboard

Challenge: Long-context understanding is a critical capability for large language models . evaluating this capability requires extensive human annotation, which is time-consuming and costly.
Approach: They propose a benchmark to assess citation-grounded long-context reasoning in academic writing.
Outcome: The proposed benchmark compares state-of-the-art models with human experts on two tasks . human experts achieve 90% accuracy, but most models struggle with the cloze-style task .
Systematic Evaluation of Predictive Fairness (2022.aacl-main)

Copied to clipboard

Challenge: Several methods have been proposed to mitigate bias in training on biased datasets.
Approach: They propose to examine the effect of target class imbalance and stereotyping on model performance by analyzing binary classification, profession prediction and regression tasks.
Outcome: The proposed methods show that data conditions have a strong influence on relative model performance.
Grounding learning of modifier dynamics: An application to color naming (D19-1)

Copied to clipboard

Challenge: Existing models for grounding are unable to understand modified color expressions, such as “light blue”.
Approach: They propose a model that learns more complex transformations in RGB space and a hard ensemble model that selects a color space depending on the modifier-color pair.
Outcome: The proposed model performs better in the HSV color space than the state-of-the-art model.
Decoupling Adversarial Training for Fair NLP (2021.findings-acl)

Copied to clipboard

Challenge: Existing work assumes main task labels and protected attributes are available in the dataset, but protected labels are often unavailable or only available in limited numbers.
Approach: They propose a method which uses only a small volume of protected labels to train adversarial models using a dataset with a discriminator.
Outcome: The proposed method can be used to transfer private-labelled instances from one dataset to another without requiring large amounts of protected labels.
Do-Not-Answer: Evaluating Safeguards in LLMs (2024.findings-eacl)

Copied to clipboard

Challenge: a dataset evaluating harmful capabilities in large language models is available at https://github.com/Libr-AI/do-not-answer.
Approach: They collect an open-source dataset to evaluate the safeguards in large language models . they find that simple BERT-style classifiers can achieve results comparable to GPT-4 .
Outcome: The proposed dataset compares the safety of six popular LLMs to GPT-4 on automatic safety evaluation.
NAT: Enhancing Agent Tuning with Negative Samples (2025.naacl-long)

Copied to clipboard

Challenge: Existing methods for fine-tuning and reinforcement learning use only positive examples, limiting their efficiency in low-resource scenarios.
Approach: They propose a method that leverages both successful and failed trajectories for fine-tuning, maximizing the utility of limited resources.
Outcome: The proposed method surpasses existing methods, including SFT, DPO, and PPO, across various tasks.
VIEWS: Entity-Aware News Video Captioning (2024.emnlp-main)

Copied to clipboard

Challenge: Existing video captioning benchmarks and models produce generic captions for videos that lack specific identification of individuals, locations, or organizations.
Approach: They propose a task of directly summarizing news videos into captions that are entity-aware . they validate the effectiveness of their approach across three video captioning models .
Outcome: The proposed approach is effective across three video captioning models.
Diverse Adversaries for Mitigating Bias in Training (2021.eacl-main)

Copied to clipboard

Challenge: Existing adversarial methods only partially mitigate the problem of model bias, added to which their training procedures are unstable.
Approach: They propose a method where discriminators are encouraged to learn orthogonal hidden representations from one another to reduce model bias.
Outcome: The proposed method significantly reduces bias and stability of training over standard methods.
Nanda Family: Open-Weights Generative Large Language Models for Hindi (2026.eacl-long)

Copied to clipboard

Challenge: Large language models remain predominantly English-centric, which limits their utility for underrepresented languages.
Approach: They propose to extend Llama’s vocabulary with 20% Hindi-specific tokens, thus halving Hindi tokenization fertility while preserving English efficiency.
Outcome: The proposed models outperform open-weight models of comparable size on a 65B-token corpus and bilingual instruction and safety alignment on . a culturally grounded dataset.
Does Representational Fairness Imply Empirical Fairness? (2022.findings-aacl)

Copied to clipboard

Challenge: Neural methods have been trained on datasets which embody cultural and societal stereotypes, captured in spurious correlations between target labels and protected attributes.
Approach: They propose a debiasing method that encourages a latent space that separates instances based on target label, while mixing instances that share protected attributes.
Outcome: The proposed method shows that representational fairness does not imply empirical fairness across methods.
Demystifying Instruction Mixing for Fine-tuning Large Language Models (2024.acl-srw)

Copied to clipboard

Challenge: Instruction tuning is effective for aligning large language models with human instructions, but the procedure to optimizing the mixing of instruction datasets is still unclear.
Approach: They categorize instructions into three primary types: NLP downstream tasks, coding, and general chat.
Outcome: The proposed method improves performance of large language models (LLMs) but it is difficult to combine different instruction datasets to optimize overall performance.
Fair Enough: Standardizing Evaluation and Model Selection for Fairness Research in NLP (2023.eacl-main)

Copied to clipboard

Challenge: Modern NLP systems exhibit a range of biases, which a growing literature on model debiasing attempts to correct.
Approach: They propose to clarify the current situation and plot a course for meaningful progress in fair learning by making clear inter-relations among the current gamut of methods and their relation to fairness theory.
Outcome: The proposed approach addresses the practical problem of model selection, which involves a trade-off between fairness and accuracy and has led to systemic issues in fairness research.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations