Papers by Lei Du

23 papers
FuxiTranyu: A Multilingual Large Language Model Trained with Balanced Data (2024.emnlp-industry)

Copied to clipboard

Challenge: Large language models exhibit significant performance discrepancies between high- and low-resource languages.
Approach: They present an open-source multilingual LLM with 8 billion parameters and a multilingual instruction dataset.
Outcome: The proposed model achieves consistent multilingual representations across languages.
Distantly Supervised Course Concept Extraction in MOOCs with Academic Discipline (2023.acl-long)

Copied to clipboard

Challenge: Existing methods to extract knowledge concepts from MOOCs are noisy and incomplete because of the limited dictionary and diverse MOOC.
Approach: They propose to automatically extract course concepts using distant supervision to eliminate the heavy work of human annotations.
Outcome: The proposed framework outperforms state-of-the-art methods with 7% absolute improvement in F1 score.
MINED: Probing and Updating with Multimodal Time-Sensitive Knowledge for Large Multimodal Models (2026.findings-acl)

Copied to clipboard

Challenge: Existing benchmarks for Large Multimodal Models (LMMs) are constrained by static representations, inadequately evaluating their ability to understand time-sensitive knowledge.
Approach: They propose a benchmark containing 2,104 time-sensitive knowledge samples spanning six knowledge types to evaluate temporal awareness along 6 key dimensions and 11 challenging tasks.
Outcome: The proposed benchmark measures temporal awareness along 6 key dimensions and 11 tasks, while most open-source LMMs still lack time understanding ability.
Distilling Large Embeddings via Hyperspherical Householder Quantization (2026.acl-long)

Copied to clipboard

Challenge: Existing methods for quantizing large embeddings rely on Euclidean quantization, which is poorly aligned with the angular geometry induced by contrastive embeddment training.
Approach: They propose a geometry-aware distillation method that compresses large embeddings into short discrete representations via iterative Householder transformations on the unit hypersphere.
Outcome: The proposed method reduces decoding cost and maintains strong semantic retrieval accuracy.
Multi-Agent Collaboration via Cross-Team Orchestration (2025.findings-acl)

Copied to clipboard

Challenge: Large Language Models (LLMs) have significantly impacted various domains, especially through organized LLM-driven autonomous agents.
Approach: They propose a framework that enables orchestrated teams to jointly propose various task-oriented solutions and interact with their insights in a self-independence while cross-team collaboration environment for superior solutions generation.
Outcome: Experiments show that the framework can generate better software quality compared to state-of-the-art frameworks.
Instance-Guided Prompt Learning for Few-Shot Text Matching (2022.findings-emnlp)

Copied to clipboard

Challenge: Few-shot text matching is a more practical technique to determine whether two texts are semantically identical.
Approach: They propose a pluggable prompt learning method for few-shot text matching . they use the semantics of instances to regulate the effects of the gate on the prompt tokens .
Outcome: The proposed method outperforms baselines on MRPC and QQP.
CLMTracing: Black-box User-level Watermarking for Code Language Model Tracing (2025.emnlp-main)

Copied to clipboard

Challenge: Open-source code language models (code LMs) are a growing threat for intellectual property protection.
Approach: They propose a black-box code LM watermarking framework that uses rule-based watermarks and utility-preserving injection method for user-level model tracing.
Outcome: The proposed framework shows that it performs well across multiple state-of-the-art code LMs and is harmless compared to existing baselines.
Augmenting Legal Judgment Prediction with Contrastive Case Relations (2022.coling-1)

Copied to clipboard

Challenge: Existing legal judgment prediction methods only consider one case fact description as input, which may not fully utilize information in the data such as case relations and frequency.
Approach: They propose a new perspective that introduces some contrastive case relations to construct case triples as input and a corresponding judgment prediction framework with case triple modeling.
Outcome: The proposed framework can be used to refine encoding and decoding processes using three customized modules on two public datasets.
One for All: Update Parameterized Knowledge Across Multiple Models with Once Edit (2025.acl-long)

Copied to clipboard

Challenge: Existing methods for modifying large language models focus on individual models, resulting in errors and hallucinations.
Approach: They propose an ensemble-based approach that employs a plug-in model as the editing module and a dynamic weight mechanism to enhance its effectiveness.
Outcome: The proposed approach outperforms existing methods while achieving superior editing efficiency.
NL ⇒ Schedule: Evaluate Multitask Scheduling Capability of Large Language Models (2026.acl-long)

Copied to clipboard

Challenge: Existing methods for scheduling from natural language descriptions rely on experts with limited scheduling skills and domain knowledge.
Approach: They propose a model to generate a feasible schedule from natural language descriptions.
Outcome: The proposed framework achieves more robust performance than six state-of-the-art LLM+solver methods.
BAR: A Backward Reasoning based Agent for Complex Minecraft Tasks (2025.findings-acl)

Copied to clipboard

Challenge: Existing studies focus on forward reasoning based planning, but this paradigm doesn't work well for complex tasks.
Approach: They propose to decompose a task into easily executed steps by planning and use a backward reasoning based agent to make the planning starting from the terminal state.
Outcome: The proposed model outperforms existing methods and the proposed modules in a virtual environment that simulates complex tasks based on real-world scenarios.
Knowledge as A Bridge: Improving Cross-domain Answer Selection with External Knowledge (C18-1)

Copied to clipboard

Challenge: Existing approaches to answer selection are limited in domains with limited labeled data.
Approach: They propose a Knowledge-aware Attentive Network framework for cross-domain answer selection that uses the knowledge base as a bridge to enable knowledge transfer from the source domain to the target domain.
Outcome: The proposed model outperforms strong competitors by a noticeable margin in cross-domain answer selection.
Explainable Text Classification with LLMs: Enhancing Performance through Dialectical Prompting and Explanation-Guided Training (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing explanation methods that generate keywords may be less effective due to missing critical contextual information.
Approach: They propose a new method to generate explanations for possible labels using LLMs and a dialectical prompt.
Outcome: The proposed method significantly improves accuracy and explanation quality over state-of-the-art methods on multiple datasets from diverse domains.
Cooperative Denoising for Distantly Supervised Relation Extraction (C18-1)

Copied to clipboard

Challenge: Existing methods for distantly supervised relation extraction suffer from noisy labeling problem, which can severely degrade its performance.
Approach: They propose a framework for distantly supervised relation extraction that leverages text corpus and knowledge graph and a cooperative module involving their mutual learning.
Outcome: The proposed method reduces the noisy labels and achieves substantial improvement over the state-of-the-art methods.
PAGED: A Benchmark for Procedural Graphs Extraction from Documents (2024.acl-long)

Copied to clipboard

Challenge: Existing methods for extraction of procedural graphs from documents are not solving the task well.
Approach: They propose a benchmark to test automatic extraction of procedural graphs from documents . they involve three advanced large language models and enhance them with a novel self-refine strategy .
Outcome: The proposed benchmark systematically examines the progress of current methods and explores the potential of emerging large language models (LLMs) on this task.
Sequential and Repetitive Pattern Learning for Temporal Knowledge Graph Reasoning (2024.lrec-main)

Copied to clipboard

Challenge: Existing methods to learn temporal evolutional representations of entities are hard to capture the complex temporal patterns such as sequential and repetitive.
Approach: They propose a Sequential and Repetitive Pattern Learning method that captures both sequential and repetitive patterns.
Outcome: The proposed method outperforms state-of-the-art methods on four representative benchmarks on GDELT dataset, where performance improvement of MRR reaches up to 18.84%.
Half-S: Halving the Scale for Near-Lossless 4-Bit LLM Training (2026.findings-acl)

Copied to clipboard

Challenge: Existing 4-bit training pipelines rely on max-scaling, which causes representation collapse . despite this, there are limitations in the accuracy of 4-bit LLM training .
Approach: They propose a scaling strategy that uses half-scaling as a hardware-friendly default . they propose fp4 support that allows for a faster scaling of large language models .
Outcome: The proposed scaling strategy narrows the gap between theoretical optimum and BF16 while maintaining the efficiency benefits of 4-bit training.
LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding (2024.acl-long)

Copied to clipboard

Challenge: Large language models (LLMs) can only handle texts a few thousand tokens long, limiting their applications on longer sequence inputs, such as books, reports, and codebases.
Approach: They propose a bilingual, multi-task benchmark for long context understanding that extends context windows and more sophisticated memory mechanisms to improve models' long context capabilities.
Outcome: The proposed model outperforms open-source models but struggles on longer contexts.
Knowing-how & Knowing-that: A New Task for Machine Comprehension of User Manuals (2023.findings-acl)

Copied to clipboard

Challenge: Existing methods for machine reading comprehension of user manuals have trouble answering complex questions.
Approach: They propose a knowing-how & knowing-that task that requires the model to answer factoid-style, procedure-style and inconsistent questions about user manuals.
Outcome: The proposed model can answer factoid-style, procedure-style and inconsistent questions about user manuals.
Document-level Causal Relation Extraction with Knowledge-guided Binary Question Answering (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing research on Event-Event Causal Relation Extraction (ECRE) has highlighted the lack of document-level modeling and causal hallucinations.
Approach: They propose a Knowledge-guided binary Question Answering method with event structures for ECRE that utilizes cross-task knowledge in IE.
Outcome: The proposed method achieves state-of-the-art on the MECI and MAVEN-ERE datasets.
The Medical Scribe: Corpus Development and Model Performance Analyses (2020.lrec-1)

Copied to clipboard

Challenge: Existing tools to assist in clinical note generation using audio of provider-patient encounters are lacking.
Approach: They develop an annotation scheme to extract relevant clinical concepts from audio of provider-patient encounters and train a state-of-the-art tagging model.
Outcome: The proposed model is more useful than the F-scores reflect and can be used in clinical notes.
CARE: A Clue-guided Assistant for CSRs to Read User Manuals (2024.acl-long)

Copied to clipboard

Challenge: Current solutions don't fit the online custom service scenarios well due to the lack of attention to user questions and possible responses.
Approach: They propose to build a clue-guided assistant for customer service representations (CSRs) that can provide accurate responses and explicitly show explainable paths about how to arrive at these responses.
Outcome: The proposed assistant can reduce CSRs' reading burden and keep high service quality, in particular with >35% decrease in time spent and keeping a >0.75 ICC score.

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