Papers by Han Xia

13 papers
Syntax-driven Approach for Semantic Role Labeling (2022.lrec-1)

Copied to clipboard

Challenge: Existing studies focus on auto-generated syntactic knowledge to enhance semantic role labeling . experimental results show that map memories can enhance SRL .
Approach: They propose to map memories to enhance semantic role labeling by encoding auto-generated syntactic knowledge from off-the-shelf toolkits.
Outcome: The proposed model outperforms baselines and achieves state-of-the-art results on two English benchmark datasets.
Orthogonal Subspace Learning for Language Model Continual Learning (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for continual learning in language models suffer catastrophic forgetting when learning sequential tasks.
Approach: They propose an orthogonal low-rank adaptation approach for continual learning in language models that uses orthogons to learn sequentially.
Outcome: The proposed approach outperforms state-of-the-art methods on continual learning benchmarks and preserves generalization ability of LLMs on unseen tasks.
From Scores to Steps: Diagnosing and Improving LLM Performance in Evidence-Based Medical Calculations (2025.emnlp-main)

Copied to clipboard

Challenge: Existing benchmarks assess only the final answer with a wide numerical tolerance, overlooking systematic reasoning failures and potentially causing serious clinical misjudgments.
Approach: They propose a new step-by-step evaluation pipeline that assesses formula selection, entity extraction, and arithmetic computation.
Outcome: The proposed method improves the accuracy of large language models on medical benchmarks from 16.35% to 53.19%.
Facilitating Long Context Understanding via Supervised Chain-of-Thought Reasoning (2025.emnlp-main)

Copied to clipboard

Challenge: Recent advances in Large Language Models (LLMs) have enabled them to process increasingly longer sequences, ranging from 2K to 2M tokens and even beyond.
Approach: They propose a synthetic dataset in the financial domain that integrates Chain-of-Thought reasoning into LLMs in a supervised manner to facilitate effective long-context understanding.
Outcome: The proposed model outperforms standard GPT-4o-mini on the Loong benchmark and fine tunes LLaMA-3.1-8B-Instruct on the model, achieving a 28.0% gain on the financial subset.
SimpleOCR: Rendering Visual Questions to Teach MLLMs to Read (2026.findings-acl)

Copied to clipboard

Challenge: MLLMs lack visual grounding mechanism to read text embedded in images, or rely on parametric shortcuts . despite strong OCR capabilities, models suffer performance degradation of 12.7% in the VQ setting .
Approach: They propose a plug-and-play training strategy that invalidates shortcuts in text prompts . they propose 'vq' setting where text queries are rendered directly onto images .
Outcome: The proposed training strategy surpasses the base model by 5.4% and GRPO based on original images by 2.7% on four representative OOD benchmarks.
ADaPT: Token-Level Decoupling for Efficient Large Reasoning Models (2026.findings-acl)

Copied to clipboard

Challenge: Existing efficiency-oriented methods attempt to shorten or mix reasoning strategies, yet often degrade reasoning capability.
Approach: They propose a token-level dual-process framework that explicitly decouples efficiency and correctness signals during training.
Outcome: The proposed framework reduces inference cost while maintaining strong reasoning ability across multiple benchmarks.
Scaling Laws for Multilingual Language Models (2025.findings-acl)

Copied to clipboard

Challenge: Existing scaling laws for language models are limited to a limited number of languages, but they can be applied to arbitrary number of different languages.
Approach: They propose a scaling law for general-purpose decoder-only language models trained on multilingual data that shifts focus from individual languages to language families.
Outcome: The proposed scaling law can be applied to models trained on multilingual data . it can be used to predict performance across multiple languages and models .
Inverse-Q*: Token Level Reinforcement Learning for Aligning Large Language Models Without Preference Data (2024.findings-emnlp)

Copied to clipboard

Challenge: Reinforcement Learning from Human Feedback (RLHF) relies on complex methodologies like Proximal Policy Optimization (PPO) that require extensive hyper-parameter tuning and pose challenges in sample efficiency and stability.
Approach: They propose an innovative framework that leverages direct preference optimization techniques but extends them by estimating the conditionally optimal policy directly from the model’s responses.
Outcome: The proposed framework matches and exceeds the effectiveness of Proximal Policy Optimization (PPO) in terms of convergence speed and alignment of model responses with human preferences.
RoCoIns: Enhancing Robustness of Large Language Models through Code-Style Instructions (2024.lrec-main)

Copied to clipboard

Challenge: Large Language Models (LLMs) have shown remarkable capabilities in following human instructions and solving NLU tasks.
Approach: They propose to use code style instructions to replace typically natural language instructions to provide more precise instructions and strengthen the robustness of LLMs.
Outcome: The proposed method outperforms natural language models on eight robustness datasets and achieves an improvement of 5.68% in test set accuracy and a reduction of 5.66 points in Attack Success Rate (ASR).
LLMBox: A Comprehensive Library for Large Language Models (2024.acl-demos)

Copied to clipboard

Challenge: a library to facilitate the development, use, and evaluation of large language models (LLMs) is presented.
Approach: They propose a unified library to facilitate the development, use and evaluation of large language models (LLMs).
Outcome: The proposed library is based on extensive experiments in a variety of evaluation settings.
ChiMST: A Chinese Medical Corpus for Word Segmentation and Medical Term Recognition (2022.lrec-1)

Copied to clipboard

Challenge: Chinese word segmentation and named entity recognition are important tasks in natural language processing.
Approach: They develop a Chinese medical corpus annotated with Chinese word boundary and medical term information to address this problem.
Outcome: The proposed corpus will be a valuable resource for Chinese word segmentation and named entity recognition research on the medical domain.
A Neural Transition-based Joint Model for Disease Named Entity Recognition and Normalization (2021.acl-long)

Copied to clipboard

Challenge: Existing models for disease recognition and normalization ignore text surface form of each candidate concept, causing boundary inconsistency.
Approach: They propose a neural transition-based joint model to normalize disease entities from biomedical text.
Outcome: The proposed model improves on two publicly available datasets.
Complementary Learning of Aspect Terms for Aspect-based Sentiment Analysis (2022.lrec-1)

Copied to clipboard

Challenge: Existing ABSA models do not pay attention to aspect terms and their contexts . a discriminator is introduced to improve ABSA, allowing for better understanding of aspect terms .
Approach: They propose to improve ABSA by complementary learning of aspect terms . they explicitly recover aspect terms from each input sentence to better understand aspects .
Outcome: The proposed approach improves ABSA on five widely used English benchmark datasets.

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