Papers by Xuan Lu

14 papers
Are U a Joke Master? Pun Generation via Multi-Stage Curriculum Learning towards a Humor LLM (2024.findings-acl)

Copied to clipboard

Challenge: Existing research has demonstrated that the ability of large language models (LLMs) to generate humorous sentences is limited to producing 25 unique jokes.
Approach: They propose a multi-stage curriculum preference learning framework to optimize both pun structure preferences and humor preferences by a Chinese Pun dataset.
Outcome: The proposed method significantly outperforms baseline models on Chinese and English benchmark datasets.
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 Side Effects of Being Smart: Safety Risks in MLLMs’ Multi-Image Reasoning (2026.acl-long)

Copied to clipboard

Challenge: Recent advances in multimodal reasoning may pose new safety risks . evaluators neglect reasoningbased safety, where harm emerges only through MLLMs .
Approach: They introduce a benchmark for multi-image reasoning safety that includes 2,676 instances . they find that models with more advanced multi- image reasoning are more vulnerable .
Outcome: The proposed benchmark consists of 2,676 instances covering 9 multi-image relations . the results show that models with more advanced multi- image reasoning are more vulnerable .
Code-Switching Information Retrieval: Benchmarks, Analysis, and the Limits of Current Retrievers (2026.findings-acl)

Copied to clipboard

Challenge: a new study examines the performance of code-switching IR in monolingual contexts . code-witching is a pervasive linguistic phenomenon in global communication .
Approach: They propose a benchmark to evaluate code-switching IR in monolingual contexts . they propose CS-MTEB, which measures performance declines of up to 27% .
Outcome: The proposed benchmark shows that code-switching performance is degraded by 27% . the proposed benchmark is based on a dataset of mixed-language queries .
A Systematic Survey of Automatic Prompt Optimization Techniques (2025.emnlp-main)

Copied to clipboard

Challenge: Recent advances in prompt engineering have created impediments for end users to adopt . however, prompt engineering remains an impedance due to rapid advances in models, tasks, and associated best practices.
Approach: They propose to define APO as a 5-part unifying framework and categorize all relevant works based on their salient features.
Outcome: The proposed framework aims to improve the performance of large language models on various tasks.
TriageAgent: Towards Better Multi-Agents Collaborations for Large Language Model-Based Clinical Triage (2024.findings-emnlp)

Copied to clipboard

Challenge: escalation in emergency department patient visits poses challenges to efficient clinical management . Currently, hospitals rely on human experts to review clinical notes and determine case urgency .
Approach: a team of researchers develop a multi-agent framework to enhance collaborative decision-making in clinical triage.
Outcome: The proposed framework outperforms state-of-the-art LLM-based methods on three clinical triage test sets.
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.
System Prompt Hijacking via Permutation Triggers in LLM Supply Chains (2025.findings-acl)

Copied to clipboard

Challenge: Large language models (LLMs) are rapidly transforming the landscape of artificial intelligence due to the substantial resources required for training.
Approach: They propose a post-deployment attack that bypasses system prompts to compromise models . they introduce Precise Activation Guarding and Unit Deviation Sampling to protect against attack .
Outcome: The proposed attack bypasses system prompts, enabling unrestricted model outputs and safety violations.
Rethinking Multiple-Choice Questions for RLVR: Unlocking Potential via Distractor Design (2026.findings-acl)

Copied to clipboard

Challenge: Existing approaches to RLVR use multiple-choice questions as verifiable rewards . however, not all tasks provide reliable verification .
Approach: They propose a framework that actively constructs high-quality distractors to block elimination shortcuts and promote deep reasoning.
Outcome: The proposed method significantly improves reasoning capabilities of Large Language Models.
InfoEnh: Towards Multimodal Sentiment Analysis via Information Bottleneck Filter and Optimal Transport Alignment (2024.lrec-main)

Copied to clipboard

Challenge: Existing methods for multi-modal sentiment analysis have been developed to overcome these challenges.
Approach: They propose a method that utilizes a masking technique as the bottleneck for information filtering and integrates all modalities into a common feature space via domain adaptation.
Outcome: Extensive experiments on two benchmark MSA datasets show the proposed method performs better than baselines.
MultiConIR: Towards Multi-Condition Information Retrieval (2025.findings-emnlp)

Copied to clipboard

Challenge: MultiConIR is a benchmark designed to evaluate retrieval and reranking models under nuanced multi-condition query scenarios.
Approach: They propose a benchmark to evaluate retrieval and reranking models under nuanced multi-condition query scenarios.
Outcome: The proposed benchmark evaluates retrieval and reranking models under nuanced multi-condition query scenarios across five domains.
MMLU-ProX: A Multilingual Benchmark for Advanced Large Language Model Evaluation (2025.emnlp-main)

Copied to clipboard

Challenge: Existing large language model evaluation benchmarks focus on English, while current multilingual tasks lack parallel questions that specifically assess cross-lingual reasoning abilities.
Approach: They propose a comprehensive benchmark covering 29 languages, built on an English benchmark.
Outcome: The MMLU-ProX is a comprehensive benchmark covering 29 languages, built on an English benchmark.
CROSSAGENTIE: Cross-Type and Cross-Task Multi-Agent LLM Collaboration for Zero-Shot Information Extraction (2025.findings-acl)

Copied to clipboard

Challenge: Large language models struggle with producing structured output while maintaining accuracy in zero-shot information extraction (IE)
Approach: They propose a multi-agent framework that enhances zero-shot IE through multi-task collaboration.
Outcome: CROSSAGENTIE outperforms state-of-the-art models in structured prediction . the framework significantly reduces inference cost while preserving accuracy .
DEBATE, TRAIN, EVOLVE: Self‐Evolution of Language Model Reasoning (2025.emnlp-main)

Copied to clipboard

Challenge: Large language models have improved significantly in reasoning through extensive training on massive datasets.
Approach: They propose a ground truth-free training framework that uses multi-agent debate traces to evolve a single language model.
Outcome: The proposed framework achieves 8.92% accuracy gain on the GSM-PLUS dataset.

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