Papers by Yulin Wu

6 papers
Defense Against Prompt Injection Attack by Leveraging Attack Techniques (2025.acl-long)

Copied to clipboard

Challenge: Recent attacks leverage LLMs’ instruction-following abilities and their inabilities to distinguish instructions injected in the data content.
Approach: They invert the intention of prompt injection methods to develop novel defense methods based on previous training-free attack methods by repeating the attack process with the original input instruction rather than the injected instruction.
Outcome: The proposed methods outperform existing defense approaches, achieving state-of-the-art results.
EvoMD-LLM: Learning the Language of Species Evolution in Reactive Molecular Dynamics (2026.findings-acl)

Copied to clipboard

Challenge: Existing models operate on static molecular representations or rely on external tools for reasoning.
Approach: They propose a framework that reformulates species-level molecular dynamics as a symbolic temporal language modeling problem.
Outcome: The proposed model outperforms neural networks and language-based baselines on multiple temporal prediction tasks and generates plausible interpretations of reaction dynamics.
MPO: Multilingual Safety Alignment via Reward Gap Optimization (2025.acl-long)

Copied to clipboard

Challenge: Existing preference learning methods for safety alignment are monolingual and struggle with noisy multilingual data.
Approach: They propose a multilingual reward gaP optimization approach that leverages the well-aligned safety capabilities of the dominant language to improve safety alignment across multiple languages.
Outcome: Extensive experiments on three LLMs, LLaMA-3.1, Gemma-2 and Qwen2.5, validate MPO’s efficacy in multilingual safety alignment without degrading general multilingual utility.
Do Current Video LLMs Have Strong OCR Abilities? A Preliminary Study (2025.coling-main)

Copied to clipboard

Challenge: a new benchmark evaluates video-based optical character recognition (Video OCR) performance of multi-modal models in videos . the benchmark aims to improve video LLMs' ability to extract text from video content . previous benchmarks have focused on video QA, but not video-related QA.
Approach: They propose to evaluate the video OCR performance of multi-modal models in videos . they use a semi-automated approach that integrates the OCR ability of image LLMs with manual refinement .
Outcome: The proposed benchmark includes 1,028 videos and 2,961 question-answer pairs . it integrates the OCR ability of image LLMs with manual refinement .
When Retriever-Reader Meets Scenario-Based Multiple-Choice Questions (2021.findings-emnlp)

Copied to clipboard

Challenge: Scenario-based question answering (SQA) requires retrieving and reading paragraphs from a large corpus to answer a question contextualized by a long scenario description.
Approach: They propose a model where the retriever is implicitly supervised only using QA labels via a novel word weighting mechanism.
Outcome: The proposed model outperforms strong baselines on multiple-choice questions in three datasets.
LaERC-S: Improving LLM-based Emotion Recognition in Conversation with Speaker Characteristics (2025.coling-main)

Copied to clipboard

Challenge: Emotion recognition in conversation (ERC) is a task of discerning human emotions for each utterance within a conversation.
Approach: They propose a framework that uses large language models to analyze speaker characteristics . they use two-stage learning to make the models reason speaker characteristics and track emotion of the speaker .
Outcome: The proposed framework outperforms existing methods on three 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