Papers by Aaron Lee

5 papers
Discourse as a Function of Event: Profiling Discourse Structure in News Articles around the Main Event (2020.acl-main)

Copied to clipboard

Challenge: a recent study shows that news articles report context-informing content that is not necessarily relevant to main events.
Approach: They propose to use a functional discourse structure for news articles to model news content structures . they propose to integrate system predicted news structures into the annotations .
Outcome: The proposed model outperforms existing models in event coreference resolution.
DALK: Dynamic Co-Augmentation of LLMs and KG to answer Alzheimer’s Disease Questions with Scientific Literature (2024.findings-emnlp)

Copied to clipboard

Challenge: Recent advances in large language models have achieved promising performances across various applications, but the challenge of integrating long-tail knowledge continues to impede the seamless adoption of LLMs in specialized domains.
Approach: They propose a dynamic co-augmentation framework for the refinement of large language models and knowledge graphs in the context of Alzheimer's Disease.
Outcome: The proposed framework can be used to study Alzheimer's Disease (AD) using LLMs and KGs.
XMD: An End-to-End Framework for Interactive Explanation-Based Debugging of NLP Models (2023.acl-demo)

Copied to clipboard

Challenge: Existing models are susceptible to learning spurious biases that do not reflect the underlying task.
Approach: They propose an open-source framework for explanation-based model debugging that allows users to provide various forms of feedback on model explanations.
Outcome: The proposed framework improves model’s OOD performance on text classification tasks by up to 18%.
Latent Agents: A Post-Training Procedure for Internalized Multi-Agent Debate (2026.acl-long)

Copied to clipboard

Challenge: Multi-agent debate is compute-intensive and requires long transcripts before answering questions.
Approach: They propose a framework that distills multi-agent debate into a single LLM by combining debate structure learning with internalization via dynamic reward scheduling and length clipping.
Outcome: The proposed model matches or exceeds explicit multi-agent debate performance using 93% fewer tokens across multiple models and benchmarks.
From Isolation to Entanglement: When Do Interpretability Methods Identify and Disentangle Known Concepts? (2026.acl-long)

Copied to clipboard

Challenge: Existing methods to evaluate features disentangle concepts from activations of neural networks are limited by their quality . current methods for concept identification and steering are sparse autoencoders, but they are not reliable.
Approach: They propose to evaluate how well featurization methods disentangle one concept from another . they use sentiment, domain, voice, and tense to steer these features .
Outcome: The proposed evaluations show that featurization methods are insufficient to establish steering selectivity . the results suggest that steering a feature affects many concepts despite a near absence of interaction effects.

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