Papers by Lianwei Wu

9 papers
DTCA: Decision Tree-based Co-Attention Networks for Explainable Claim Verification (2020.acl-main)

Copied to clipboard

Challenge: Recent methods to discover evidence for explainable claim verification are nontransparent and unexplained.
Approach: They propose a Decision Tree-based Co-Attention model to discover evidence for explainable claim verification using neural networks.
Outcome: The proposed model boosts the F1-score by more than 3.11%, 2.41% on two public datasets.
Step-by-Step: Controlling Arbitrary Style in Text with Large Language Models (2024.lrec-main)

Copied to clipboard

Challenge: Existing methods for autoregressive text generation have low controllability and accumulating errors.
Approach: They propose a three-stage prompt-based approach to express autoregressive text in a specific region editing task using a word frequency-based strategy.
Outcome: Experiments on publicly competitive datasets confirm that the proposed approach achieves state-of-the-art performance.
Cultivating Forensic Reasoning for Generalizable Multimodal Manipulation Detection (2026.acl-long)

Copied to clipboard

Challenge: Existing methods for manipulation detection and grounding focus on manipulator type classification under result-oriented supervision.
Approach: They propose a reasoning-driven framework that shifts learning from outcome fitting to process modeling.
Outcome: The proposed framework achieves state-of-the-art with superior generalization on large-scale datasets.
From Form to Logic: Masked Reconstruction and Reasoning Distillation for Short Video Fake News Detection (2026.acl-long)

Copied to clipboard

Challenge: Existing detectors that detect short video fake news suffer from global-alignment bias and lack generative reasoning are too late.
Approach: They propose a Perception-Cognition Dual-driven Detector that jointly observes the form and probes the logic for short video fake news detection.
Outcome: The proposed detector outperforms baseline detectors on real-world datasets while improving interpretability and robustness in data scarcity scenarios.
Zero-shot Cross-lingual Conversational Semantic Role Labeling (2022.findings-naacl)

Copied to clipboard

Challenge: Xu et al., 2021: conversational semantic role labeling is under-explored in non-Chinese languages due to the lack of multilingual CSRL annotations for the parser training.
Approach: They propose a model that implicitly learns conversational structure-aware representations with hierarchical encoders and elaborately designed pre-training objectives.
Outcome: The proposed model outperforms baselines on English CSRL tests by large margins . it will facilitate the research of non-Chinese dialogue tasks which suffer from ellipsis and anaphora .
Unified Dual-view Cognitive Model for Interpretable Claim Verification (2021.acl-long)

Copied to clipboard

Challenge: Existing studies constructing direct interactions between the claim and each single user response to capture evidence have shown remarkable success in interpretable claim verification.
Approach: They propose a Dual-view model based on the views of Collective and Individual Cognition (CICD) that captures word-level semantics based . on individual cognition, they adjust the proportion between them to generate global evidence.
Outcome: The proposed model is based on the views of collective and individual cognition and achieves state-of-the-art performance on three benchmark datasets.
Generating Attribution Reports for Manipulated Facial Images: A Dataset and Baseline (2026.acl-long)

Copied to clipboard

Challenge: Existing facial forgery detection methods focus on binary classification or pixel-level localization, providing little semantic insight into the nature of the manipulation.
Approach: They propose a multimodal task that localizes forged regions and generates natural language explanations grounded in editing process.
Outcome: The proposed task localizes forged regions and generates natural language explanations grounded in editing process.
STRIDE-ED: A Strategy-Grounded Stepwise Reasoning Framework for Empathetic Dialogue Systems (2026.acl-long)

Copied to clipboard

Challenge: Empathetic dialogue requires not only recognizing a user’s emotional state but also making strategy-aware, context-sensitive decisions throughout response generation.
Approach: They propose a STRategy-grounded, interpretable, and DEep reasoning framework that models Empathetic Dialogue through structured, strategy-conditioned reasoning.
Outcome: The proposed framework outperforms existing methods on automatic metrics and human evaluations.
Different Absorption from the Same Sharing: Sifted Multi-task Learning for Fake News Detection (D19-1)

Copied to clipboard

Challenge: Existing methods for detecting fake news use shared features as complementarity features without selection.
Approach: They propose a sifted multi-task learning method with a selected sharing layer for fake news detection.
Outcome: The proposed method boosts the F1-score by more than 0.87%, 1.31% on two public and widely used competition datasets.

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