Papers by Xinhao Li

6 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.
SEARL: Joint Optimization of Policy and Tool Graph Memory for Self-Evolving Agents (2026.acl-long)

Copied to clipboard

Challenge: Recent advances in Reinforcement Learning with Verifiable Rewards (RLVR) have demonstrated significant potential in single-turn reasoning tasks.
Approach: They propose a tool-memory based self-evolving agentic framework that integrates planning with execution.
Outcome: The proposed framework is able to extract explicit knowledge from historical data and leverage inter-trajectory correlations to densify reward signals.
Open-World Authorship Attribution (2025.findings-acl)

Copied to clipboard

Challenge: Existing benchmarks for large language models do not evaluate their performance in academic research . authors aim to identify authors from anonymous text without additional information .
Approach: They propose a benchmark to quantitatively assess LLMs' ability to infer author from text . they propose 'open-world' authorship attribute' to be a two-stage framework .
Outcome: The proposed approach achieves 60.7% accuracy and 44.3% accuracy in two stages.
Diving into Mitigating Hallucinations from a Vision Perspective for Large Vision-Language Models (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing benchmarks focus on coarse-grained hallucination detection and fail to capture hallucinics . vision encoders exhibit unique hallucinian characteristics, but suboptimal of simple feature fusion.
Approach: They propose a visual encoder that employs different training paradigms to instill inductive biases in visual encoded models.
Outcome: The proposed system reduces hallucinations and improves model performance.
UniGeM: Unifying Data Selection and Mixing via Geometric Exploration and Mining (2026.findings-acl)

Copied to clipboard

Challenge: Large Language Models (LLMs) scaling is limited by data quality and domain mixing and instance selection are two separate problems.
Approach: They propose a framework that unifies mixing and selection without training proxy models or relying on external reference datasets.
Outcome: The proposed framework achieves 2.0 data efficiency over a random baseline and further improves overall performance compared to SOTA methods in reasoning-heavy evaluations and multilingual generalization.
Extending LLM Context Window with Adaptive Grouped Positional Encoding: A Training-Free Method (2025.acl-long)

Copied to clipboard

Challenge: Existing long-context training data is scarce and requires substantial GPU resources for training.
Approach: They propose a training-free plug-and-play method to enhance long-context understanding in existing large language models.
Outcome: The proposed method outperforms existing LLMs on various tasks and surpasses baseline methods.

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