Papers by Lei Liao

17 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 .
ViLPAct: A Benchmark for Compositional Generalization on Multimodal Human Activities (2023.findings-eacl)

Copied to clipboard

Challenge: a vision-language benchmark for human activity planning is designed for humans . the task is easy for humans, but challenging for SOTA deep learning models .
Approach: They propose a vision-language benchmark for human activity planning that extends Charades with intents and builds on a multi-choice question test set.
Outcome: The proposed benchmark evaluates the ability of systems to anticipate and plan human actions in a multimodal visionlanguage setting.
Efficiently Identifying Watermarked Segments in Mixed-Source Texts (2025.acl-long)

Copied to clipboard

Challenge: Existing methods for watermarking entire documents neglect identifying individual watermark segments within long, mixed-source documents.
Approach: They propose a framework for partial watermark detection that detects whether there is a watermark segment in long text and an adaptive online learning algorithm to pinpoint the precise location of watermark segments.
Outcome: The proposed framework outperforms existing methods and is adaptable to other watermarking techniques.
Dialogue State Tracking with Incremental Reasoning (2021.tacl-1)

Copied to clipboard

Challenge: Empirical results show that our method outperforms the state-of-the-art methods in terms of joint belief accuracy.
Approach: They propose to track dialogue states gradually with reasoning over dialogue turns using the back-end data.
Outcome: Empirical results show that the proposed method outperforms state-of-the-art methods in terms of joint belief accuracy for a large-scale human–human dialogue dataset.
WildDoc: How Far Are We from Achieving Comprehensive and Robust Document Understanding in the Wild? (2025.emnlp-main)

Copied to clipboard

Challenge: Existing benchmarks for document understanding in the wild are based on scanned or digital documents . however, these benchmarks fail to capture the challenges posed by documents in the real world .
Approach: They propose a new benchmark that incorporates a diverse set of manually captured document images reflecting real-world conditions.
Outcome: The proposed model is based on a set of manually captured document images reflecting real-world conditions and is compared with digital or scanned documents.
Resource-Friendly Dynamic Enhancement Chain for Multi-Hop Question Answering (2025.findings-acl)

Copied to clipboard

Challenge: Existing approaches to solve multi-hop question answering challenges require multiple rounds of retrieval and iterative generation.
Approach: They propose a framework that decomposes complex questions into coherent subquestions . it then iteratively refines these subquests through context-aware rewriting to generate effective query formulations.
Outcome: The proposed framework performs on par with or surpasses state-of-the-art benchmarks while significantly reducing token consumption.
Context-Aware Hierarchical Taxonomy Generation for Scientific Papers via LLM-Guided Multi-Aspect Clustering (2025.emnlp-main)

Copied to clipboard

Challenge: Existing taxonomy construction methods lack coherence and granularity . Existing approaches rely on manual or narrowly defined schemes .
Approach: They propose a context-aware hierarchical taxonomy generation framework that integrates LLMs with dynamic clustering.
Outcome: The proposed method outperforms existing methods in taxonomy coherence, granularity, and interpretability.
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.
Beyond Code Pairs: Dialogue-Based Data Generation for LLM Code Translation (2026.acl-long)

Copied to clipboard

Challenge: Large language models (LLMs) have shown remarkable capabilities in code translation, yet their performance deteriorates in low-resource programming domains such as Fortran and emerging frameworks like CUDA .
Approach: They propose a dual-LLM Questioner–Solver pipeline that integrates external knowledge from compilers and runtime feedback to generate verified translations and multi-turn dialogues.
Outcome: The proposed model outperforms proprietary models on key metrics like compilation success and accuracy.
Prompting and Evaluating Large Language Models for Proactive Dialogues: Clarification, Target-guided, and Non-collaboration (2023.findings-emnlp)

Copied to clipboard

Challenge: Recent studies have shown that ChatGPT has limitations such as failing to ask clarifying questions to ambiguous queries or refusing problematic user requests.
Approach: They propose a Proactive Chain-of-Thought prompting scheme which augments LLMs with the goal planning capability over descriptive reasoning chains to trigger proactivity.
Outcome: The proposed scheme augments LLMs with the goal planning capability over descriptive reasoning chains to trigger the proactivity of LLM-based proactive dialogue systems.
Leave No Document Behind: Benchmarking Long-Context LLMs with Extended Multi-Doc QA (2024.emnlp-main)

Copied to clipboard

Challenge: Existing benchmarks for evaluating long-context language models employ irrelevant noise texts to artificially extend the length of test cases, diverging from the real-world scenarios of long-constituency applications.
Approach: They propose a long-context benchmark, Loong, aligning with realistic scenarios through extended multi-document question answering (QA) .
Outcome: The proposed model can scale up the context window of large language models to perform in-depth analysis of multiple long documents.
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.
SoftDedup: an Efficient Data Reweighting Method for Speeding Up Language Model Pre-training (2024.acl-long)

Copied to clipboard

Challenge: Current methods focus on detecting and removing duplicates, which risks the loss of valuable information and neglects the varying degrees of duplication.
Approach: They propose a method that maintains dataset integrity while selectively reducing the sampling weight of data with high commonness.
Outcome: The proposed method significantly improves training efficiency on deduplicated datasets and improves downstream accuracy by 1.77%.
Retrieval over Classification: Integrating Relation Semantics for Multimodal Relation Extraction (2025.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to multimodal relation extraction ignore structural constraints and lack semantic expressiveness for fine-grained relation understanding.
Approach: They propose a framework that reformulates multimodal relation extraction as a retrieval task driven by relation semantics.
Outcome: The proposed framework achieves state-of-the-art performance on the benchmark datasets MNRE and MORE and exhibits stronger robustness and interpretability.
A.S.E: A Repository-Level Benchmark for Evaluating Security in AI-Generated Code (2026.findings-acl)

Copied to clipboard

Challenge: Existing security evaluation benchmarks lack relevance to real-world AI programming tasks . current LLMs struggle with secure coding, research shows .
Approach: They propose a repository-level evaluation benchmark to assess security of AI-generated code.
Outcome: The proposed framework mirrors real-world AI programming tasks and offers valuable insights into the state of AI code generation.
Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting (2025.findings-acl)

Copied to clipboard

Challenge: Current document image parsing solutions rely on specialized models or generate content autoregressively.
Approach: They propose a multimodal document image parsing model that integrates specialized models with autogeneous content generation.
Outcome: The proposed model achieves state-of-the-art performance across diverse page-level and element-level settings while ensuring superior efficiency.

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