Papers by Xinyuan Li

9 papers
AgenticEval: Toward Agentic and Self-Evolving Safety Evaluation of Large Language Models (2026.findings-acl)

Copied to clipboard

Challenge: Existing static safety evaluation methods are ill-equipped to address dynamic nature of AI risks and evolving regulations, creating a critical safety gap.
Approach: They propose a new paradigm of agentic safety evaluation reframing evaluation as a continuous and self-evolving process rather than a one-time audit.
Outcome: The proposed framework shows a consistent decline in model safety as the evaluation hardens.
SOLAR: Serendipity Optimized Language Model Aligned for Recommendation (2025.findings-emnlp)

Copied to clipboard

Challenge: Large Language Models have shown strong potential in recommendation tasks . however, their application to serendipity-oriented recommendations remains challenging .
Approach: They propose a domain-adaptive instruction tuning method that aligns Large Language Models with recommendation tasks.
Outcome: The proposed framework bridges the domain gap between LLMs and recommendation tasks.
TagRAG: Tag-guided Hierarchical Knowledge Graph Retrieval-Augmented Generation (2026.findings-acl)

Copied to clipboard

Challenge: Existing approaches to retrieval-augmented generation rely on fragment-level retrieval . GraphRAG suffers from inefficiencies in information extraction and costly resource consumption .
Approach: They propose a tag-guided hierarchical knowledge graph RAG framework for efficient global reasoning and scalable graph maintenance.
Outcome: GraphRAG achieves an average win rate of 78.36% on a dataset spanning agriculture, computer science, law, and cross-domain settings compared with baselines .
Joint Embedding of Words and Labels for Text Classification (P18-1)

Copied to clipboard

Challenge: Existing approaches to text classification use word embeddings to capture semantic regularities between words.
Approach: They propose to view text classification as a label-word joint embedding problem . they use a framework that measures compatibility between text sequences and labels .
Outcome: The proposed framework outperforms the state-of-the-art methods on large text datasets.
COCOGEC: Counterfactual Generation for Robust Grammatical Error Correction (2026.findings-acl)

Copied to clipboard

Challenge: Existing GEC models fail to understand error patterns in varying contexts . a framework that generates copies of training instances with error-irrelevant contexts altered is proposed .
Approach: They propose a framework that generates copies of training instances with error-irrelevant contexts altered.
Outcome: The proposed framework outperforms baselines on the simulated tasks and outperformed existing models.
Efficient KL Divergence Estimation via Truncated Top-K Integration for Large Language Models (2026.acl-long)

Copied to clipboard

Challenge: Existing methods for estimating KL divergence using only top-k tokens suffer from high variance or systematic bias.
Approach: They propose a top-k Importance-weighted KL Estimator that exploits the Zipfian structure of language model distributions by integrating only the top-K tokens.
Outcome: The proposed estimator outperforms existing estimators on multiple benchmarks while exhibiting lower variance.
SuLoRA: Subspace Low-Rank Adaptation for Parameter-Efficient Fine-Tuning (2025.findings-acl)

Copied to clipboard

Challenge: Existing methods for fine-tuning large language models (LLMs) introduce parameter interference, leading to a gap in generalization performance for specific tasks compared to full fine-uning.
Approach: They propose a parameter-separated low-rank adapter to account for task differences by decomposing LoRA’s parameter matrix into multiple independent subspaces and assigning them differentially to distinct tasks.
Outcome: The proposed method outperforms LoRA in trainable parameter efficiency and overall model performance on various NLP tasks.
DiffusionAttacker: Diffusion-Driven Prompt Manipulation for LLM Jailbreak (2025.emnlp-main)

Copied to clipboard

Challenge: Large Language Models (LLMs) are susceptible to generating harmful content when prompted with carefully crafted inputs, a vulnerability known as LLM jailbreaking.
Approach: They propose an end-to-end generative approach for jailbreak rewriting inspired by diffusion models that uses a sequence-tosequence (seq2sequ) diffusion model as a generator, conditioning on the original prompt and guiding the denoising process with a novel attack loss.
Outcome: Experiments on Advbench and Harmbench show that the proposed method outperforms autoregressive jailbreak models across evaluation metrics including ASR, fluency, diversity and diversity.
Large Language Models are Good Annotators for Type-aware Data Augmentation in Grammatical Error Correction (2025.coling-main)

Copied to clipboard

Challenge: Large Language Models (LLMs) have demonstrated outstanding performance in many downstream tasks due to their emergent and in-context learning abilities.
Approach: They propose a method that considers LLMs as annotators for type-aware data augmentation in GEC tasks.
Outcome: The proposed method can generate consistent and typeaware data, which could improve the performance of large language models.

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