Papers by Xiangyu Lin

9 papers
Mitigating Hallucinations of Large Language Models in Medical Information Extraction via Contrastive Decoding (2024.findings-emnlp)

Copied to clipboard

Challenge: Medical Information Extraction (MIE) tasks are a fundamental component of medical NLP.
Approach: They propose an alternative adaptive constraint strategy to adjust the scale and scope of contrastive tokens.
Outcome: The proposed approach selectively enhances the identification and classification capabilities while minimizing the influence of other inherent abilities in LLMs.
AdapTime: Enabling Adaptive Temporal Reasoning in Large Language Models (2026.findings-acl)

Copied to clipboard

Challenge: Existing methods for temporal reasoning are limited and apply a fixed pipeline to all questions.
Approach: They propose an adaptive temporal reasoning method that dynamically executes reasoning steps based on context and task requirements.
Outcome: Experiments on two temporal QA benchmarks show the proposed method works.
LongAttn: Selecting Long-context Training Data via Token-level Attention (2025.findings-acl)

Copied to clipboard

Challenge: Existing methods to select long-context data often rely on sentence-level analysis, which can be greatly optimized in both performance and efficiency.
Approach: They propose a token-level framework which quantifies long-range dependencies for LLMs by calculating token-based dependency strength and distribution uniformity of token scores.
Outcome: The proposed framework quantifies long-range dependencies, enabling more accurate and efficient data selection.
Can LLMs Hear the Dogwhistle? (2026.findings-acl)

Copied to clipboard

Challenge: Existing safety benchmarks focus on explicitly harmful content, but ignore context-dependent expressions such as dogwhistles.
Approach: They propose a benchmark for evaluating LLM safety under dogwhistle-driven prompts . their findings expose a blind spot in current safety evaluation practices .
Outcome: The proposed benchmark compared safety performance with toxic terms using dogwhistle-driven prompts.
Self-distilled Transitive Instance Weighting for Denoised Distantly Supervised Relation Extraction (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing approaches to reducing wrongly labeled instances are based on a bag-level setting . however, sentence-level training is vulnerable to the noise brought by DS, which limits its application.
Approach: They propose a transitive instance weighting mechanism integrated with the self-distilled BERT backbone to generate dynamic instance weights for denoised sentence-level training.
Outcome: The proposed method can tackle wrongly labeled instances and prevent overfitting.
Regularized Attentive Capsule Network for Overlapped Relation Extraction (2020.coling-main)

Copied to clipboard

Challenge: Existing methods to extract relations from distant supervision contain low-quality instances with noisy words and overlapped relations.
Approach: They propose a Regularized Attentive Capsule Network to better identify overlapped relations in informal sentences . they embed multi-head attention into the capsule network as the low-level capsules .
Outcome: Extensive experiments show that the proposed model improves relation extraction.
Distantly Supervised Relation Extraction using Multi-Layer Revision Network and Confidence-based Multi-Instance Learning (2021.emnlp-main)

Copied to clipboard

Challenge: Distantly supervised relation extraction is used in knowledge bases but its low quality and noisy sentences are present in sentence bags.
Approach: They propose a multi-layer revision network which emphasizes inner-sentence correlations before extracting relevant information within sentences.
Outcome: The proposed method improves on two New York Times datasets.
MultiDx: A Multi-Source Knowledge Integration Framework towards Diagnostic Reasoning (2026.findings-acl)

Copied to clipboard

Challenge: Existing approaches focus on diagnostic reasoning based on internal model knowledge or static knowledge bases.
Approach: They propose a two-stage diagnostic reasoning framework that integrates multi-perspective evidence to generate a diagnostic prediction.
Outcome: The proposed method generates suspected diagnoses and reasoning traces from web search, SOAP-formatted case, and clinical case database.
Multi-perspective Improvement of Knowledge Graph Completion with Large Language Models (2024.lrec-main)

Copied to clipboard

Challenge: Knowledge graph completion (KGC) is a widely used method to tackle incompleteness in knowledge graphs (KGs).
Approach: They propose a general framework to compensate for the deficiency of contextualized knowledge by querying large language models from various perspectives.
Outcome: The proposed framework improves knowledge graph completion (KGC) by querying large language models from various perspectives.

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