Papers by Xuan Wu

13 papers
I Learn Better If You Speak My Language: Understanding the Superior Performance of Fine-Tuning Large Language Models with LLM-Generated Responses (2024.emnlp-main)

Copied to clipboard

Challenge: Recent research has demonstrated that a large language model (LLM) can generate training data for another LLM, or for creating supplementary training materials, such as rationales.
Approach: They conduct an in-depth investigation to understand why fine-tuning an LLM with responses generated by a LLM often yields better results than using responses generated from humans.
Outcome: The proposed approach can be used to transfer knowledge from a larger model to a smaller one, or for creating supplementary training materials, such as rationales.
MalURLBench: A Benchmark Evaluating Agents’ Vulnerabilities When Processing Web URLs (2026.findings-acl)

Copied to clipboard

Challenge: Existing models struggle to detect elaborately disguised malicious URLs, despite their ability to process malicious URL's.
Approach: They propose a benchmark to evaluate LLMs’ vulnerabilities to malicious URLs and a lightweight defense module to mitigate the vulnerability.
Outcome: The proposed framework analyzes 61,845 attack instances spanning 10 real-world scenarios and 7 categories of real malicious websites.
The Pragmatic Mind of Machines: Tracing the Emergence of Pragmatic Competence in Large Language Models (2026.eacl-long)

Copied to clipboard

Challenge: Current large language models (LLMs) have demonstrated emerging capabilities in social intelligence tasks, including implicature resolution and theory-of-mind reasoning.
Approach: They introduce a dataset grounded in the pragmatic concept of alternatives to evaluate whether large language models can accurately infer nuanced speaker intentions.
Outcome: The proposed model can infer nuanced speaker intentions by inferring the speaker’s intended meaning and explaining when and why a speaker would choose one utterance over its alternative.
Multi-Task Reinforcement Learning for Enhanced Multimodal LLM-as-a-Judge (2026.acl-industry)

Copied to clipboard

Challenge: Existing MLLMs are optimized for single-task scenarios and struggle to generalize to diverse contexts.
Approach: They propose a framework that integrates multitask reinforcement learning and generalization capabilities of MLLMs to optimize the judge model across multiple tasks.
Outcome: The proposed framework outperforms baseline models in judgment consistency and correlation with human preferences.
AskToAct: Enhancing LLMs Tool Use via Self-Correcting Clarification (2025.emnlp-main)

Copied to clipboard

Challenge: Existing tools for ambiguous and incomplete queries are limited by manual construction and lack of error correction mechanisms during multi-turn clarification.
Approach: They propose a framework that exploits the mapping between queries and their tool invocation solutions by removing key parameters from queries while retaining them as ground truth.
Outcome: The proposed framework outperforms existing methods while maintaining high accuracy in tool invocation.
Searching for Best Practices in Retrieval-Augmented Generation (2024.emnlp-main)

Copied to clipboard

Challenge: Retrieval-augmented generation (RAG) techniques have proven to be effective in integrating up-to-date information, mitigating hallucinations, and enhancing response quality, especially in specialized domains.
Approach: They propose several strategies for deploying RAG that balance performance and efficiency.
Outcome: The proposed approaches can significantly enhance question-answering capabilities and accelerate the generation of multimodal content using a “retrieval as generation” strategy.
Rethinking Token Reduction for State Space Models (2024.emnlp-main)

Copied to clipboard

Challenge: Existing methods for token reduction for SSMs lead to performance drops . a recent study shows that Mamba-2 improves the accuracy of the model by 5.7% to 13.1% .
Approach: They propose a token reduction method that integrates token importance and similarity into SSMs and takes advantage of pruning and merging.
Outcome: The proposed method improves accuracy by 5.7% to 13.1% on six benchmarks with Mamba-2 compared to existing methods while reducing computational demands and memory requirements.
ERNIE-M: Enhanced Multilingual Representation by Aligning Cross-lingual Semantics with Monolingual Corpora (2021.emnlp-main)

Copied to clipboard

Challenge: Existing methods for pretraining cross-lingual models are limited in their size due to the limited amount of parallel corpora.
Approach: They propose a method that encourages the model to align multiple languages with monolingual corpora to overcome the constraint of the parallel corpus size.
Outcome: The proposed method outperforms existing cross-lingual models and delivers new state-of-the-art results in various cross-linguistic downstream tasks.
Logical Form Generation via Multi-task Learning for Complex Question Answering over Knowledge Bases (2022.coling-1)

Copied to clipboard

Challenge: Existing generation-based KBQA methods that translate natural language questions to executable logical forms are proving promising but noise introduced can lead to incorrect results.
Approach: They propose a Generation-based KBQA method that uses auxiliary information to enhance logical form generation by combining unseen KB items with novel combinations.
Outcome: The proposed method achieves state-of-the-art results on ComplexWebQuestions and WebQuestIONSSP datasets.
GASim: A Graph-Accelerated Hybrid Framework for Social Simulation (2026.acl-long)

Copied to clipboard

Challenge: Large-scale social simulators require high latency due to expensive memory retrieval and sequential ABM execution.
Approach: They propose a graph-accelerated hybrid multi-agent framework for large-scale social simulations that uses large language models and numerical agent-based models to scale up simulations.
Outcome: The proposed framework delivers 9.94 speedup over the traditional framework and consumes less than 20% of tokens.
Sparse-to-Dense: A Free Lunch for Lossless Acceleration of Video Understanding in LLMs (2025.acl-short)

Copied to clipboard

Challenge: Recent advances in Video Large Language Models (Video-LLMs) have achieved exceptional performance on tasks like video question answering and captioning.
Approach: They propose a decoding strategy that leverages sparse top-K attention and dense full attention to accelerate Video-LLMs without loss.
Outcome: The proposed approach achieves a 1.94 walltime speedup in video processing.
Bi-DCSpell: A Bi-directional Detector-Corrector Interactive Framework for Chinese Spelling Check (2024.findings-emnlp)

Copied to clipboard

Challenge: Chinese Spelling Check (CSC) aims to detect and correct potentially misspelled characters in Chinese sentences.
Approach: They propose a bi-directional Detector-Corrector framework for Chinese Spelling Check which mutually enhances the feature representation for detection and correction subtasks.
Outcome: The proposed framework reduces the risk of over-correction and under-corrections while preserving the knowledge learnt from correction.
SusGen-GPT: A Data-Centric LLM for Financial NLP and Sustainability Report Generation (2025.findings-naacl)

Copied to clipboard

Challenge: Existing tools for financial reporting and ESG analysis are lacking . large language models are not proficient across general finance and ESE domains .
Approach: They propose a dataset that includes seven financial NLP tasks and a benchmark to improve sustainability report generation.
Outcome: SusGen-30k, a high-quality dataset, shows state-of-the-art performance . it surpasses all other models except GPT-4 in six adapted tasks and two off-the shelf tasks .

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