Papers by Derek Li

9 papers
Can LLMs Learn Uncertainty on Their Own? Expressing Uncertainty Effectively in A Self-Training Manner (2024.emnlp-main)

Copied to clipboard

Challenge: Large language models (LLMs) exhibit excessive, random, and uninformative uncertainty rendering them unsuitable for decision-making in human-computer interactions.
Approach: They propose an uncertainty-aware instruction tuning method that aligns LLMs’ perception with the probabilistic uncertainty of the generation.
Outcome: The proposed method improves LLMs' performance by 45.2%, with reasonably good out-of-domain generalization capabilities.
DQA: Diagnostic Question Answering for IT Support (2026.acl-industry)

Copied to clipboard

Challenge: a diagnostic question-answering framework maintains persistent diagnostic state and aggregates retrieved cases at the level of root causes rather than individual documents.
Approach: They propose a diagnostic question-answering framework that maintains persistent diagnostic state . it aggregates retrieved cases at the level of root causes rather than individual documents .
Outcome: The framework achieves a 78.7% success rate under trajectory-level success criterion compared to a multi-turn RAG baseline . the framework reduces average turns from 8.4 to 3.9, compared with a single-turn baseline crim.
Can LMs Generalize to Future Data? An Empirical Analysis on Text Summarization (2023.emnlp-main)

Copied to clipboard

Challenge: Existing summarization benchmarks overlap in time with pre-training corpora and fine-tuning datasets.
Approach: They propose a temporal generalization benchmark that contains data samples from 2010 to 2022 to understand the temporal ability of abstractive summarization models.
Outcome: The proposed benchmark analyzes data samples from 2010 to 2022 to understand the temporal generalization ability of abstractive summarization models.
Introducing Semantics into Speech Encoders (2023.acl-long)

Copied to clipboard

Challenge: Existing self-supervised speech encoders contain primarily acoustic rather than semantic information.
Approach: They propose a task-agnostic unsupervised way to incorporate semantic information from large language model (LLM) systems into self-supervised speech encoders without labeled audio transcriptions.
Outcome: The proposed approach improves spoken language understanding (SLU) performance by over 5% on intent classification (IC), with modest gains in named entity resolution (NER) and slot filling (SF), and spoken question answering (SQA) score by over 22%.
CoEvol: Constructing Better Responses for Instruction Finetuning through Multi-Agent Cooperation (2024.emnlp-main)

Copied to clipboard

Challenge: Recent studies have focused on constructing substantial quantities of IFT data with minimal human effort.
Approach: They propose a multi-agent cooperation framework for the improvement of IFT responses for large language models using a debate-advise-edit-judge paradigm.
Outcome: The proposed framework outperforms baseline models on unseen tasks and shows that it can improve instruction-following capabilities on large language models.
Scaling is Not All You Need: Clinical-Oriented Reinforcement Learning Makes Parameter-Efficient Clinical Reasoning (2026.findings-acl)

Copied to clipboard

Challenge: Large language models are increasingly used in medicine, but expert-level clinical reasoning remains a high-complexity, high-stakes frontier.
Approach: They propose to train clinical reasoning models using a Reasoning-Oriented Data Strategy based on topological synthesis and CoT cold-start.
Outcome: The proposed pipeline outperforms existing models and outperformed the strongest open-source alternatives up to 671B in MedXpertQA.
Towards Demonstration-Aware Large Language Models for Machine Translation (2024.findings-acl)

Copied to clipboard

Challenge: Large language models for machine translation often face difficulties in leveraging demonstrations to further improve their performance.
Approach: They propose a novel approach that integrates demonstration-aware training and inference strategies within the framework of tuning-based LTMs.
Outcome: The proposed model integrates demonstration-aware training and inference strategies within tuning-based LTMs.
Not Your Typical Government Tipline: LLM-Assisted Routing of Environmental Protection Agency Citizen Tips (2025.emnlp-main)

Copied to clipboard

Challenge: Regulatory agencies often operate with limited resources and rely on tips to identify violations . but processing these tips at scale presents significant operational challenges . a case study shows advances in large language models can be utilized to support overburdened agencies .
Approach: They analyze thousands of citizen tips from the EPA's "Report a Violation" system to develop an LLM-assisted pipeline for tip routing.
Outcome: The proposed approach filters out 80.5% of irrelevant tips and increases overall routing accuracy from 31.8% to 82.4% compared to the current system.
ViStruct: Visual Structural Knowledge Extraction via Curriculum Guided Code-Vision Representation (2023.emnlp-main)

Copied to clipboard

Challenge: State-of-the-art vision-language models have limited performance in structural knowledge extraction, such as relations between objects.
Approach: They propose to leverage the inherent structure of programming language to depict visual structural information in a well-organized structured format.
Outcome: The proposed framework improves visual structural knowledge extraction on visual structure prediction tasks.

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