Papers by Minzhi Li

9 papers
Retrieving Multimodal Information for Augmented Generation: A Survey (2023.findings-emnlp)

Copied to clipboard

Challenge: Large Language Models (LLMs) are increasingly using multimodality to augment their generation ability, but there is no unified perception of at which stage and how to incorporate different modalities.
Approach: They propose to use multimodality to augment Large Language Models (LLMs) this will provide scholars with a deeper understanding of the methods' applications and encourage them to adapt existing techniques to the fast-growing field of LLMs.
Outcome: The proposed methods improve factuality, reasoning, interpretability, and robustness of the generated content.
Interactive Learning for LLM Reasoning (2026.findings-acl)

Copied to clipboard

Challenge: Existing multi-agent learning approaches foster collaboration among Large Language Models (LLMs) yet they still rely on re-executing the MAS during inference.
Approach: They propose a co-learning framework that integrates Dynamic Interaction and Perception Calibration to enhance LLMs' independent problem-solving ability.
Outcome: The proposed framework integrates Dynamic Interaction and Perception Calibration to improve LLMs' independent problem-solving ability.
Social Intelligence Data Infrastructure: Structuring the Present and Navigating the Future (2024.findings-acl)

Copied to clipboard

Challenge: Existing work on social intelligence in NLP does not provide a coherent subfield for researchers to analyze and identify research gaps and future directions.
Approach: They build a social AI taxonomy and a data library of 480 NLP datasets to analyze existing datasets and evaluate language models’ performance in different social intelligence aspects.
Outcome: The proposed infrastructure analyzes existing dataset efforts and evaluates language models’ performance in different social intelligence aspects.
DnA-Eval: Enhancing Large Language Model Evaluation through Decomposition and Aggregation (2025.coling-main)

Copied to clipboard

Challenge: Large Language Models (LLMs) are scalable and economical evaluators, but how reliable they are is still under-explored.
Approach: They propose a framework which breaks down the evaluation process into decomposition and aggregation stages based on pedagogical practices and provides an interpretable window for how well LLMs evaluate .
Outcome: The proposed framework improves performance on a variety of meta-evaluation benchmarks by providing an interpretable window for how well LLMs evaluate .
Inducing Positive Perspectives with Text Reframing (2022.acl-long)

Copied to clipboard

Challenge: Sentiment transfer is a text style transfer task that aims to reverse sentiment polarity and reversal in meaning.
Approach: They propose a task called positive reframing that neutralizes a negative point of view and generates 'positive' perspectives without contradicting original meaning.
Outcome: The proposed model neutralizes a negative point of view and generates 'positive' perspectives without contradicting the original meaning.
Navigating Ethical Challenges in NLP: Hands-on strategies for students and researchers (2025.acl-tutorials)

Copied to clipboard

Challenge: This tutorial will equip participants with basic guidelines for thinking deeply about ethical issues . participants will gain practical experience on when to flag a paper for ethics review .
Approach: This tutorial will equip participants with basic guidelines for thinking deeply about ethical issues . participants will gain practical experience on when to flag a paper for ethics review .
Outcome: This tutorial will equip participants with basic guidelines for thinking deeply about ethical issues . participants will gain practical experience on when to flag a paper for ethics review .
Mind the Gap: Static and Interactive Evaluations of Large Audio Models (2025.acl-long)

Copied to clipboard

Challenge: Recent work has focused on evaluating large audio models (LAMs) that directly accept audio inputs.
Approach: They propose an interactive approach to evaluate large audio models and collect 7,500 LAM interactions from 484 participants.
Outcome: The proposed model is based on a set of user-generated audio interfaces with 7,500 interactions from 484 participants.
Distilling an End-to-End Voice Assistant Without Instruction Training Data (2025.acl-long)

Copied to clipboard

Challenge: Recent efforts to train speech-only LLMs have led to models “forging” speech information from text-only models.
Approach: They propose a paradigm for training Speech Large Language Models without instruction data by using the response of a text-only LLM to transcripts as self-supervision.
Outcome: The proposed model generalizes to Spoken Question Answering, Classification, and Translation and achieves a 72% win rate compared with state-of-the-art models like Qwen 2 Audio .
CoAnnotating: Uncertainty-Guided Work Allocation between Human and Large Language Models for Data Annotation (2023.emnlp-main)

Copied to clipboard

Challenge: Annotated data plays a critical role in training models and evaluating their performance.
Approach: They propose a paradigm for Human-LLM co-annotation of unstructured texts at scale that utilizes uncertainty to estimate LLMs’ annotation capability.
Outcome: The proposed model outperforms existing models on many text-annotation tasks with up to 21% performance improvement over random baseline.

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