Papers by Xingyu Lin

4 papers
ARise: Towards Knowledge-Augmented Reasoning via Risk-Adaptive Search (2025.acl-long)

Copied to clipboard

Challenge: Large language models (LLMs) have impressive capabilities but their application in open-ended, knowledge-intensive, complex reasoning scenarios is limited.
Approach: They propose a framework that integrates risk assessment of intermediate reasoning states with dynamic retrieval-augmented generation within a Monte Carlo tree search paradigm.
Outcome: The proposed framework outperforms the state-of-the-art KAR methods by up to 23.10% and the latest RAG-equipped large reasoning models by upto 25.37%.
DocMMIR: A Framework for Document Multi-modal Information Retrieval (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing multi-modal information retrieval models lack a comprehensive exploration of document-level retrieval . existing models suffer from the absence of cross-domain datasets at this granularity.
Approach: They propose a multi-modal document retrieval framework to unify diverse document formats and domains with a comprehensive retrieval scenario.
Outcome: The proposed framework improves document retrieval performance on a large multimodal dataset.
End-to-End Open-Domain Question Answering with BERTserini (N19-4)

Copied to clipboard

Challenge: a new open-domain question answering system integrates best practices from IR with a BERT-based reader to identify answers from a large corpus of Wikipedia articles.
Approach: They propose an end-to-end question answering system that integrates BERT with an IR reader.
Outcome: The proposed system improves on a standard benchmark test collection.
Token-Level Policy Optimization: Linking Group-Level Rewards to Token-Level Aggregation via sequence-level likelihood (2026.acl-long)

Copied to clipboard

Challenge: Group Relative Policy Optimization (GRPO) has significantly advanced the reasoning ability of large language models (LLMs).
Approach: They propose a token-level framework that leverages sequence-level likelihood to link group-level rewards with individual tokens via token- level aggregation and introduces a KL-Divergence mask constraint that targets tokens with positive advantages and decreasing entropy to mitigate abrupt policy updates.
Outcome: Experiments show that TEPO achieves state-of-the-art performance on mathematical reasoning benchmarks and reduces convergence time by 50% compared with GRPO/DAPO.

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