Papers by Xu Wenqiang

6 papers
Equipping Retrieval-Augmented Large Language Models with Document Structure Awareness (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing approaches to retrieval-augmented generation ignore valuable structure that is crucial for document organization.
Approach: They propose a framework that explicitly incorporates structural information throughout the RAG process.
Outcome: The proposed framework incorporates structural information throughout the RAG process.
Revisit Automatic Error Detection for Wrong and Missing Translation – A Supervised Approach (D19-1)

Copied to clipboard

Challenge: Current machine translation techniques are bottlenecked by adequacy issues . we propose automatic detection of missing and wrong translations .
Approach: They propose automatic detection of adequacy errors in MT hypothesis for MT model evaluation by annotating missing and wrong translations in 15000 Chinese-English translation pairs.
Outcome: The proposed model can detect missing and wrong translations in 15000 Chinese-English translation pairs.
ConReader: Exploring Implicit Relations in Contracts for Contract Clause Extraction (2022.emnlp-main)

Copied to clipboard

Challenge: Existing CCE methods treat contracts as plain text, creating a barrier to understanding complex contracts.
Approach: They propose a framework to model implicit relations in legal contracts to improve contract understanding . they propose Term-Definition Relation captures the relation between important terms and their definitions .
Outcome: The proposed framework improves on two CCE tasks in conventional and zero-shot settings.
AntCritic: Argument Mining for Free-Form and Visually-Rich Financial Comments (2024.lrec-main)

Copied to clipboard

Challenge: Argument mining is a thriving task in natural language processing, but its generalization is limited by existing datasets.
Approach: They propose to use a dataset to help model argument mining . the dataset AntCritic supports both argument component detection and argument relation prediction tasks.
Outcome: The proposed model can detect arguments and identify their relationships automatically.
ViT-TTS: Visual Text-to-Speech with Scalable Diffusion Transformer (2023.emnlp-main)

Copied to clipboard

Challenge: Text-to-speech (TTS) performance has improved with the advent of denoising Diffusion Probabilistic Models . however, perceived quality of audio depends on content, pitch, rhythm, and energy .
Approach: They propose a visual TTS model with scalable diffusion transformers that complement phoneme sequences with visual information to generate high-perceived audio.
Outcome: The proposed model outperforms existing models regardless of visibility of the scene . it can generate high-perceived audio, opening up new avenues for AR and VR applications .
Crab: A Novel Configurable Role-Playing LLM with Assessing Benchmark (2025.acl-long)

Copied to clipboard

Challenge: Existing RP-LLMs employ only a single role with numerous dialogues, but Crab enables dynamic configuration of desired roles, thereby enhancing related flexibility and adaptability.
Approach: They propose a Configurable Role-Playing LLM with Assessing Benchmark that combines a Role dataset curation, persona-emodying Llm construction, and comprehensive benchmark creation for RP dialogue generation.
Outcome: The proposed model outperforms existing LLMs in performing fine-grained evaluations of RP while keeping dialogue per role minimal.

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