Papers by Wenqi Shi

10 papers
MedAdapter: Efficient Test-Time Adaptation of Large Language Models Towards Medical Reasoning (2024.emnlp-main)

Copied to clipboard

Challenge: Large language models (LLMs) have improved generation and reasoning capabilities compared to traditional BERT-sized models due to massive number of parameters and extensive pre-training on vast textual corpora.
Approach: They propose a unified post-hoc adapter for test-time adaptation of large language models . they propose to fine-tune only a small BERT-sized adapter to rank candidate LLMs .
Outcome: The proposed adapter improves performance on four biomedical tasks without requiring computational resources or sharing data with third parties.
BMRetriever: Tuning Large Language Models as Better Biomedical Text Retrievers (2024.emnlp-main)

Copied to clipboard

Challenge: Developing effective biomedical retrieval models is important for excelling at knowledge-intensive biomedically tasks but still challenging due to the lack of sufficient publicly annotated biomedic data and computational resources.
Approach: They propose a series of dense retrievers for enhancing biomedical retrieval via unsupervised pre-training on large biomedically corpora, followed by instruction fine-tuning on a combination of labeled datasets and synthetic pairs.
Outcome: Experiments on 5 biomedical tasks across 11 datasets confirm the performance of the retrieval model on various biomedically demanding tasks.
EHRAgent: Code Empowers Large Language Models for Few-shot Complex Tabular Reasoning on Electronic Health Records (2024.emnlp-main)

Copied to clipboard

Challenge: EHRAgent enables clinicians to interact with EHRs using natural language . reliance on rule-based conversion systems often necessitates additional training or effort from data engineers.
Approach: They propose a large language model agent that generates and executes code in natural language to facilitate clinicians in directly interacting with EHRs.
Outcome: The proposed agent outperforms the strongest baseline by up to 29.6% in success rate on three real-world EHR datasets.
WorkForceAgent-R1: Incentivizing Reasoning Capability in LLM-based Web Agents via Reinforcement Learning (2026.findings-eacl)

Copied to clipboard

Challenge: Existing web agents relying on supervised fine-tuning struggle with generalization and robustness due to insufficient reasoning capabilities when handling the inherently dynamic nature of web interactions.
Approach: They propose a large language model-empowered web agent that trains using a rule-based reinforcement learning framework to enhance single-step reasoning and planning for business-oriented web navigation tasks.
Outcome: The proposed agent outperforms baseline LLM-based agents on the WorkArena benchmark by 10.26–16.59%.
MIMIR: A Customizable Agent Tuning Platform for Enhanced Scientific Applications (2024.emnlp-demo)

Copied to clipboard

Challenge: Large language models (LLMs) have evolved into interactive agents capable of planning, tool use, and task execution across various tasks.
Approach: They propose a platform that leverages large language models to generate agent-tuning data for fine-tuneing smaller, specialized models.
Outcome: MIMIR enables large models to simulate various roles and create interaction data, which can then be used to fine-tune open-source models like LLaMA2.
Towards Effective and Efficient Multi-Agent Language Model Systems: Foundations, Prospects, and Applications (2026.acl-tutorials)

Copied to clipboard

Challenge: Multi-agent systems powered by large language models still face challenges . tutorial focuses on three core components to build effective and efficient systems .
Approach: This tutorial introduces recent advances in building effective and efficient multi-agent LLM systems . it focuses on three core components: model distillation, dynamic routing, memory- and compute efficient serving .
Outcome: This tutorial introduces state-of-the-art techniques for building efficient and efficient multi-agent LLM systems . it covers coordination and communication among agents, crucial for collective performance .
Knowledge-Infused Prompting: Assessing and Advancing Clinical Text Data Generation with Large Language Models (2024.findings-acl)

Copied to clipboard

Challenge: Clinical natural language processing (NLP) is a subfield that requires the extraction, analysis, and interpretation of unstructured clinical text.
Approach: They propose a model which infuses knowledge into clinical text generation with LLMs for clinical NLP tasks.
Outcome: The proposed model improves performance across 8 clinical NLP tasks and 18 datasets by 7.7%-8.7% on average.
RAM-EHR: Retrieval Augmentation Meets Clinical Predictions on Electronic Health Records (2024.acl-short)

Copied to clipboard

Challenge: Existing deep learning models for EHRs rely on knowledge from a single source and do not capture the semantic information for medical codes.
Approach: They propose a Retrieval AugMentation pipeline to augment clinical prediction on EHRs . they use multiple knowledge sources to convert them into text and use consistency regularization to capture complementary information from patient visits and summarized knowledge.
Outcome: Experiments on two EHR datasets show that RAM-EHR improves clinical prediction tasks.
RAG in the Wild: On the (In)effectiveness of LLMs with Mixture-of-Knowledge Retrieval Augmentation (2026.findings-acl)

Copied to clipboard

Challenge: Retrieval-augmented generation (RAG) enhances large language models by integrating external knowledge retrieved at inference time.
Approach: They evaluate RAG systems using MassiveDS, a large-scale datastore with mixture of knowledge.
Outcome: The proposed approach improves performance on knowledge-intensive NLP tasks.
ROSE: An Intent-Centered Evaluation Metric for NL2SQL (2026.acl-long)

Copied to clipboard

Challenge: Existing evaluation metrics for evaluating the effectiveness of Natural Language to SQL (NL2SQL) solutions are becoming unreliable due to its sensitiveness to syntactic variation and inconsistent consistency with ground-truth SQL.
Approach: They propose an intent-centered metric that focuses on whether the predicted SQL answers the question, rather than consistency with the ground-truth SQL.
Outcome: The proposed metric outperforms the next-best metric by nearly 24% on the expert-aligned validation set **ROSE-VEC**.

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