Papers by Lei Fan

27 papers
QUITO-X: A New Perspective on Context Compression from the Information Bottleneck Theory (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for compressing context by removing redundant tokens are inconsistent with the objective of retaining the most important tokens when conditioning on a given query.
Approach: They propose a method that uses information bottleneck theory to compress context . they propose to remove redundant tokens using metrics such as self-information or perplexity .
Outcome: The proposed method achieves a 25% increase in compression rate compared to the state-of-the-art .
Evaluating Generative Language Models in Information Extraction as Subjective Question Correction (2024.lrec-main)

Copied to clipboard

Challenge: Modern large language models (LLMs) perform poorly in elementary tasks like relation extraction and event extraction due to two issues in conventional evaluation methods.
Approach: They propose a method to evaluate large language models by incorporating a human annotation schema.
Outcome: The proposed evaluation method improves matching between model outputs and golden labels.
Can We Edit Factual Knowledge by In-Context Learning? (2023.emnlp-main)

Copied to clipboard

Challenge: In-context knowledge editing (IKE) is a new paradigm for NLP research that can be applied to large language models with tens or hundreds of parameters.
Approach: They propose to use in-context knowledge editing (IKE) without gradient updating to edit factual knowledge without a gradient update.
Outcome: The proposed method achieves a competitive success rate compared to gradient-based methods on GPT-J but with fewer side effects.
Alignment for Efficient Tool Calling of Large Language Models (2025.emnlp-main)

Copied to clipboard

Challenge: Recent advances in tool learning have enabled large language models to integrate external tools, enhancing their task performance by expanding their knowledge boundaries.
Approach: They propose a framework that combines probabilistic knowledge boundary estimation with dynamic decision-making to allow LLMs to better assess when to invoke tools based on their confidence.
Outcome: The proposed framework shows significant improvements in tool efficiency by reducing unnecessary tool usage.
Alleviating Hallucinations from Knowledge Misalignment in Large Language Models via Selective Abstention Learning (2025.acl-long)

Copied to clipboard

Challenge: Large language models (LLMs) suffer from severe hallucination issues due to the knowledge misalignment between the pre-training stage and the supervised fine-tuning stage.
Approach: They propose a training objective with an abstention mechanism that selectively rejects tokens that misalign with the desired knowledge distribution via a special [REJ] token.
Outcome: The proposed model selectively rejects tokens that misalign with the desired knowledge distribution via a special [REJ] token.
Learning to Ask Denotative and Connotative Questions for Knowledge-based VQA (2024.findings-emnlp)

Copied to clipboard

Challenge: Large language models have attracted increasing attention due to their prominent performance on various tasks.
Approach: They propose to let LLMs learn to ask informative questions to collect visual information . they introduce concepts of denotation and connotation to promote image and question understanding .
Outcome: The proposed model can generate high-quality questions and efficiently collect required information without expensive training or annotations.
Towards IP Intelligence: Benchmarking Large Language Models on Intellectual Property Knowledge and Practice (2026.findings-acl)

Copied to clipboard

Challenge: Existing datasets and benchmarks focus only on patents or cover limited aspects of the IP field, lacking alignment with real-world scenarios.
Approach: They propose a bilingual IP task taxonomy and a large-scale bilingual benchmark to evaluate LLMs in real-world IP practice.
Outcome: The proposed model achieves only 75.8% accuracy, indicating room for improvement . open-source IP and law-oriented models lag behind closed-source general-purpose models .
Empathy in Diversity: Personalized Depression and Anxiety Therapy via Dialogue State Tracking and Patient-Aware Planning (2026.acl-long)

Copied to clipboard

Challenge: Recent efforts have turned to large language models (LLMs) as therapeutic agents for psychological therapy tasks, yet robustness across diverse patients remains underexplored.
Approach: They propose a realistic role-play protocol for evaluating therapeutic dialogue agents and a de-identified, expert-annotated corpus of therapist–patient dialogues.
Outcome: The proposed framework outperforms baselines on therapeutic outcomes and dialogue quality while improving conversational efficiency.
SLAM: Towards Efficient Multilingual Reasoning via Selective Language Alignment (2025.coling-main)

Copied to clipboard

Challenge: Large language models (LLMs) have demonstrated significant improvements in reasoning abilities, but these improvements are primarily focused on English, leading to inferior performance in non-English scenarios.
Approach: They propose a multilingual reasoning alignment approach that fine-tunes the layers responsible for multilingual comprehension in one stage.
Outcome: The proposed method fine-tunes 6 of the 9 layers responsible for multilingual comprehension, while reducing training time by 4.1-11.9 compared to the two-stage method.
Live-Aid: A Large-Scale Dialogue Dataset and Benchmark for Interleaved Multi-party Interactions in Live Streaming (2026.findings-acl)

Copied to clipboard

Challenge: Existing Multimodal Large Language Models struggle with dynamic interactions due to the scarcity of high-quality interleaved data.
Approach: They propose a large-scale interleaved live interaction Chinese dataset with human-annotated video responses.
Outcome: The proposed model can be used to evaluate live interactions in Chinese over 1,100 hours and 80,037 dialogue turns.
Structural Supervision for Word Alignment and Machine Translation (2022.findings-acl)

Copied to clipboard

Challenge: Existing knowledge on syntactic structure neglects the rich structural information from target tokens and the structural similarity between the source and target sentences.
Approach: They propose to incorporate syntactic structure of both source and target tokens into the encoder-decoder framework, tightly correlating the internal logic of word alignment and machine translation for multi-task learning.
Outcome: The proposed method outperforms baselines on four publicly available language pairs and consistently outperformed baselines in alignment accuracy and translation quality.
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.
Language-Specific Layer Matters: Efficient Multilingual Enhancement for Large Vision-Language Models (2025.findings-emnlp)

Copied to clipboard

Challenge: Large vision-language models exhibit an imbalance in multilingual capabilities .
Approach: They propose a training recipe that achieves efficient multilingual enhancement for LVLMs by Precise Language Specific layers fine-tuning.
Outcome: The proposed training recipe achieves efficient multilingual enhancement for LVLMs by fine-tuning language specific layers.
FlowSearch: Advancing Deep Research with Dynamic Structured Knowledge Flow (2026.acl-long)

Copied to clipboard

Challenge: FlowSearch is a multi-agent framework that actively constructs and evolves a dynamic structured knowledge flow to drive subtask execution and reasoning.
Approach: They propose a multi-agent framework that actively constructs and evolves a dynamic structured knowledge flow to drive subtask execution and reasoning.
Outcome: The proposed framework achieves competitive performance on GAIA, HLE, GPQA and TRQA benchmarks and is available to download.
Read Anywhere Pointed: Layout-aware GUI Screen Reading with Tree-of-Lens Grounding (2024.emnlp-main)

Copied to clipboard

Challenge: Existing models for GUI understanding ignore a key GUI-referring task: screen reading based on user-indicated points.
Approach: They propose a Tree-of-Lens agent that constructs a Hierarchical Layout Tree based on user input points and a GUI screenshot.
Outcome: The proposed agent can interpret the Screen Point-and-Read task on mobile, web, and operating systems.
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.
MMLU-ProX: A Multilingual Benchmark for Advanced Large Language Model Evaluation (2025.emnlp-main)

Copied to clipboard

Challenge: Existing large language model evaluation benchmarks focus on English, while current multilingual tasks lack parallel questions that specifically assess cross-lingual reasoning abilities.
Approach: They propose a comprehensive benchmark covering 29 languages, built on an English benchmark.
Outcome: The MMLU-ProX is a comprehensive benchmark covering 29 languages, built on an English benchmark.
UNO Arena for Evaluating Sequential Decision-Making Capability of Large Language Models (2024.emnlp-main)

Copied to clipboard

Challenge: Existing LLMs demonstrate powerful capabilities between tasks, but can they make sequential decisions?
Approach: They propose to evaluate sequential decision-making capability of large language models (LLMs) using novel metrics based Monte Carlo methods.
Outcome: The proposed benchmark improves sequential decision-making performance compared to the vanilla LLM player.
CLFFRD: Curriculum Learning and Fine-grained Fusion for Multimodal Rumor Detection (2024.lrec-main)

Copied to clipboard

Challenge: Existing multimodal rumor detection models overlook sample difficulty and order when training . Existing models overlook text-level difficulty, image-level and multimodal difficulty when training samples .
Approach: They propose a curriculum learning framework that uses fine-grained fusion to detect rumors . they propose fusion-based methods that combine text and images to enhance semantic cohesion .
Outcome: The proposed framework outperforms state-of-the-art models on English and Chinese benchmark datasets.
Scaling Behaviors of LLM Reinforcement Learning Post-Training: An Empirical Study in Mathematical Reasoning (2026.acl-long)

Copied to clipboard

Challenge: elucidating scaling laws for large language models (LLMs) during pre-training remains unexplored.
Approach: They characterize how model scale, data, and compute interact during pre-training . they find that large models consistently demonstrate superior compute and data efficiency .
Outcome: The proposed scaling laws offer practical guidance for scaling reasoning capabilities through reinforcement learning post-training.
Advancing Large Language Model Attribution through Self-Improving (2024.emnlp-main)

Copied to clipboard

Challenge: Teaching large language models to generate text with citations to evidence sources requires high-quality attribution data, which is costly and labor-intensive.
Approach: They propose a framework for iteratively improving the attribution capability of large language models (LLMs) by attributing output to verifiable sources.
Outcome: Experiments on three open-domain question-answering datasets show that START improves in aggregating information across multiple sources.
A Novel Negative Sample Generation Method for Contrastive Learning in Hierarchical Text Classification (2025.coling-main)

Copied to clipboard

Challenge: Existing methods for hierarchical text classification struggle with fine-grained labels, leading to difficulties in accurate classification.
Approach: They propose a hierarchical sequence ranking method for generating diverse negative samples using hierarchically structured hierarchic labels.
Outcome: The proposed method achieves state-of-art (SOTA) on two datasets showing that it can distinguish between fine-grained labels and discriminate.
Improving Contextual Faithfulness of Large Language Models via Retrieval Heads-Induced Optimization (2025.acl-long)

Copied to clipboard

Challenge: Existing frameworks for retrieval-augmented large language models (LLMs) are lacking in LFQA faithfulness testing.
Approach: They propose a framework to teach retrieval-augmented large language models to explicitly discriminate between faithful and unfaithful generations.
Outcome: The proposed framework outperforms GPT-4o in LFQA scenarios and outperformed existing benchmarks.
Hyperlink-induced Pre-training for Passage Retrieval in Open-domain Question Answering (2022.acl-long)

Copied to clipboard

Challenge: Existing methods to train dense passage retrieval have a large data gap between upstream and downstream relevance.
Approach: They propose a method to pre-train the dense retriever with the text relevance induced by hyperlinks within Web documents.
Outcome: The proposed method outperforms existing methods under different scenarios and in the open-domain question answering domain.
Untangle the KNOT: Interweaving Conflicting Knowledge and Reasoning Skills in Large Language Models (2024.lrec-main)

Copied to clipboard

Challenge: Existing studies have explained to what extent LLMs extract conflicting knowledge from the provided text, but they neglect the necessity to reason with conflicting information.
Approach: They construct a dataset for knowledge conflict resolution examination in the form of question answering that divides reasoning with conflicting knowledge into three levels.
Outcome: The proposed dataset enables analysis of reasoning with conflicting knowledge in the form of question answering.
KuiLeiXi: a Chinese Open-Ended Text Adventure Game (2021.acl-demo)

Copied to clipboard

Challenge: Recent advances in pre-trained language models have made it possible to generate human-like text.
Approach: They propose to integrate an open-ended text adventure game in Chinese, named KuiLeiXi, where players interact with the AI until the plot goals are reached.
Outcome: The proposed game lacks incentives and relies on players to explore on their own.

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