Papers by Mengting Zhang

14 papers
Modalities Should Be Appropriately Leveraged: Uncertainty Guidance for Multimodal Chinese Spelling Correction (2024.lrec-main)

Copied to clipboard

Challenge: Chinese spelling correction (CSC) aims to detect and correct spelling errors in Chinese texts.
Approach: They propose a framework that incorporates uncertainty into feature learning and correction stages . they propose to combine the uncertainty of multimodal features with model learning .
Outcome: The proposed framework improves on three public datasets.
E-NER: Evidential Deep Learning for Trustworthy Named Entity Recognition (2023.findings-acl)

Copied to clipboard

Challenge: Named entity recognition (NER) systems focus on improving model performance, ignoring the need to quantify model uncertainty.
Approach: They propose to introduce two uncertainty-guided loss terms to the conventional EDL and a series of uncertainty-guiding training strategies to solve these challenges.
Outcome: The proposed method achieves better OOV/OOD detection performance and generalization ability on OOV entities compared to state-of-the-art methods.
Structural Patent Classification Using Label Hierarchy Optimization (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for patent classification ignore key technical content claims and citation relationships . existing methods treat labels as independent targets, failing to exploit semantic and structural information within the label taxonomy.
Approach: They propose a Claim Structure based Patent Classification model with Label Awareness . structural graph learning is used to mine the internal logic of patent claims .
Outcome: The proposed method is more effective than state-of-the-art classification models.
CAN: Constrained Attention Networks for Multi-Aspect Sentiment Analysis (D19-1)

Copied to clipboard

Challenge: Existing methods for aspect-specific sentiment classification are noisy and downgraded performance.
Approach: They propose a constrained attention network to regularize attention for multi-aspect sentiment analysis by orthogonal regularization on multiple aspects and sparse regularization for each single aspect.
Outcome: The proposed approach outperforms state-of-the-art methods on two public datasets and extends to multi-task settings.
Uncertainty-Aware Unlikelihood Learning Improves Generative Aspect Sentiment Quad Prediction (2023.findings-acl)

Copied to clipboard

Challenge: Existing studies focus on what to generate but ignore what not to generate . a template-agnostic method boosts original learning and reduces mistakes simultaneously .
Approach: They propose a template-agnostic method to control the token-level generation . they introduce Monte Carlo dropout to understand the built-in uncertainty of pre-trained language models .
Outcome: The proposed method boosts original learning and reduces mistakes simultaneously on four public datasets.
Simple but Effective Compound Geometric Operations for Temporal Knowledge Graph Completion (2024.acl-long)

Copied to clipboard

Challenge: Current methods embed factual knowledge into continuous vector space and apply geometric operations to learn potential patterns in temporal knowledge graphs.
Approach: They propose a temporal knowledge graph completion method that uses two geometric operations to learn missing facts in temporal graphs.
Outcome: The proposed method significantly outperforms existing temporal knowledge graph embedding models.
KBM: Delineating Knowledge Boundary for Adaptive Retrieval in Large Language Models (2025.findings-emnlp)

Copied to clipboard

Challenge: Retrieval-augmented generation (RAG) is employed to tackle these challenges . a Knowledge Boundary Model (KBM) is used to express the known/unknown of a given question .
Approach: They propose a Knowledge Boundary Model to express the known/unknown of a given question . they find that not all questions need to trigger RAG to improve performance .
Outcome: The proposed model reduces time and computational costs by retrieving parts of unknown knowledge . the proposed model can express the known/unknown of a given question and determine whether a RAG needs to be triggered .
TRUST: Towards Robust Social Bot Detection via Uncertainty-Guided Pseudo-Labeling and Graph Structure Purification (2026.findings-acl)

Copied to clipboard

Challenge: Existing graph-based detection models are vulnerable to deceptive message propagation, where bots deliberately interact with legitimate users.
Approach: They propose a framework to mitigate deceptive message propagation by node-level uncertainty estimation and graph structure purification.
Outcome: The proposed framework improves on three benchmark datasets and six GNN backbones on real-world social bots.
SudokuFill: A Multi-Agent Progressive Filling Framework for Document-Level Scientific Information Extraction (2026.findings-acl)

Copied to clipboard

Challenge: Scientific information extraction (SciIE) is a key bottleneck for turning unstructured papers into computable knowledge bases.
Approach: They propose a scientific information extraction framework that solves a Sudoku problem as a progressive filling problem.
Outcome: The proposed framework outperforms the GPT-4o model on a document-level adjuvant dataset.
UBench: Benchmarking Uncertainty in Large Language Models with Multiple Choice Questions (2025.findings-acl)

Copied to clipboard

Challenge: Existing methods for benchmarking the uncertainty of large language models face challenges . existing methods require internal model access, additional training, or high computational costs .
Approach: They propose a new benchmark for evaluating the uncertainty of large language models based on confidence intervals . UBench encompasses 11,978 multiple choice questions spanning knowledge, language, understanding, and reasoning capabilities.
Outcome: The proposed method outperforms existing methods for benchmarking the uncertainty of large language models.
RECAL: Sample-Relation Guided Confidence Calibration over Tabular Data (2023.findings-emnlp)

Copied to clipboard

Challenge: Various machine learning methods for tabular data lack accurate confidence estimation, which is needed for high-risk sensitive applications such as credit modeling and financial fraud detection.
Approach: They propose a general post-training confidence calibration framework to calibrate the confidence of current machine learning models by employing graph neural networks to model the relationships between different samples.
Outcome: The proposed framework improves the confidence estimation on tabular datasets by using graph neural networks to model the relationships between different samples.
Is Compound Aspect-Based Sentiment Analysis Addressed by LLMs? (2024.findings-emnlp)

Copied to clipboard

Challenge: Aspect-based sentiment analysis (ABSA) aims to predict aspect-based elements from text . large language models (LLMs) have impressive abilities in handling human instructions .
Approach: They propose a framework to evaluate LLMs' ability to handle complex ABSA tasks . they use constrained prompts to automatically organize the returned predictions .
Outcome: The proposed framework outperforms supervised methods in some cases, but it is still lacking in other areas.
WildFeedback: Aligning LLMs With In-situ User Interactions And Feedback (2026.acl-long)

Copied to clipboard

Challenge: Traditional alignment methods rely on human annotations and are subjective and misalignment with real-world user preferences.
Approach: They propose a framework that leverages in-situ user feedback during conversations with LLMs to create preference datasets automatically.
Outcome: The proposed framework identifies and classifies user feedback to LLM responses between conversation turns and creates examples of preferred and dispreferred responses according to user preferences.
OPINE: A Prior-calibrated Scoring Framework for LLM-based Multi-label Scientific Opinion Classification (2026.findings-acl)

Copied to clipboard

Challenge: Existing methods for scientific opinion classification rely on direct label generation and are limited by the multi-label nature of scientific expressions.
Approach: They propose a framework that reformulates scientific opinion classification as a controllable pipeline.
Outcome: The proposed framework outperforms baseline models on 18 discourse functions in micro, macro, and example settings.

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