Papers by Wei Nie

12 papers
Re-ViLM: Retrieval-Augmented Visual Language Model for Zero and Few-Shot Image Captioning (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for image-to-text generation store all knowledge within parameters, thus requiring computational-expensive fine-tuning.
Approach: They propose a Retrieval-augmented Visual Language Model that stores all the knowledge within parameters and can be used to retrieve it from the external database.
Outcome: The proposed model significantly boosts performance for image-to-text generation tasks with 4x less parameters compared with baseline methods.
ULMR: Unlearning Large Language Models via Negative Response and Model Parameter Average (2024.emnlp-industry)

Copied to clipboard

Challenge: Large language models (LLMs) have attracted significant interest from the research community due to their broad applicability in many language-oriented tasks.
Approach: They propose a framework which uses pre-training datasets to rewrite instructions and generate negative responses to preserve the performance of the original LLM.
Outcome: The proposed framework can erase the pre-training data while maintaining the performance of the original model.
Unveiling and Consulting Core Experts in Retrieval-Augmented MoE-based LLMs (2024.emnlp-main)

Copied to clipboard

Challenge: Existing research seeks to enhance RAG performance by retrieving higher-quality documents or designing RAG-specific LLMs, but internal mechanisms that contribute to RAG’s effectiveness remain underexplored.
Approach: They propose to examine the internal mechanisms within the popular Mixture-of-Expert (MoE)-based LLMs and examine their ability to improve RAG by examining expert activations.
Outcome: The proposed method significantly improved the ability of Large Language Models (LLMs) to solve knowledge-intensive tasks.
AttenWalker: Unsupervised Long-Document Question Answering via Attention-based Graph Walking (2023.findings-acl)

Copied to clipboard

Challenge: Existing methods for annotating long-document question answering are based on short documents and can hardly incorporate long-range information.
Approach: They propose an unsupervised method to generate long-document question answering pairs . they propose a method to aggregate and generate answers with long-range dependency .
Outcome: The proposed method outperforms existing methods on NarrativeQA and Qasper.
Investigating BERT’s Knowledge of Language: Five Analysis Methods with NPIs (D19-1)

Copied to clipboard

Challenge: Recent work evaluating sentence representation models' knowledge of grammar has been slower to emerge.
Approach: They propose five experimental methods inspired by prior work evaluating pretrained sentence representation models to examine their grammatical knowledge.
Outcome: The proposed methods show that the model has significant knowledge of the licensing environment but its success varies widely across different methods.
Reasoning in the Dark: Interleaved Vision-Text Reasoning in Latent Space (2026.findings-acl)

Copied to clipboard

Challenge: Existing multimodal reasoning methods depend on explicit reasoning steps that require labor-intensive vision-text annotations and inherently introduce significant inference latency.
Approach: They propose a method that integrates visual and visual information into the reasoning process to improve the performance of multimodal LLMs.
Outcome: The proposed method achieves an average performance increase of 5.45% while achieving a speed increase of over 5 times compared to existing methods.
Capturing Global Structural Information in Long Document Question Answering with Compressive Graph Selector Network (2022.emnlp-main)

Copied to clipboard

Challenge: Existing methods to answer long document questions ignore the global structure of the long document, which is essential for long-range understanding.
Approach: They propose a Compressive Graph Selector Network to capture the global structure of the long document in a compressive and iterative manner.
Outcome: The proposed model outperforms existing methods on two datasets.
DiagnosisArena: Benchmarking Diagnostic Reasoning for Large Language Models (2026.findings-acl)

Copied to clipboard

Challenge: Existing medical benchmarks for diagnostic reasoning are limited in their ability to perform complex tasks.
Approach: They propose to benchmark diagnostic capabilities of large language models to assess their accuracy and generalization bottlenecks.
Outcome: The proposed model achieves 45.82%, 31.09%, and 17.79% accuracy, compared to current models, o3-mini, e1 and DeepSeek-R1 .
UniKeyphrase: A Unified Extraction and Generation Framework for Keyphrase Prediction (2021.findings-acl)

Copied to clipboard

Challenge: Mainstream methods that ignore the diversity among keyphrases or weakly capture the relation between tasks implicitly ignore keyphrase diversity.
Approach: They propose a novel end-to-end learning framework that jointly learns to extract and generate keyphrases by exploiting latent semantic relation between extraction and generation.
Outcome: The proposed approach outperforms mainstream methods on a benchmarked document on keyphrase prediction.
Robustness Testing of Language Understanding in Task-Oriented Dialog (2021.acl-long)

Copied to clipboard

Challenge: a lack of systematic studies on the robustness of language understanding models in task-oriented dialog systems is limiting . authors propose a model-agnostic toolkit LAUG to approximate natural language perturbations .
Approach: They propose a model-agnostic toolkit LAUG to approximate natural language perturbations for testing the robustness of language understanding models in task-oriented dialog systems.
Outcome: The proposed toolkit reveals critical robustness issues in state-of-the-art models.
metaCAT: A Metadata-based Task-oriented Chatbot Annotation Tool (2020.aacl-demo)

Copied to clipboard

Challenge: Creating high-quality annotated dialogue corpora necessitates a high level of human engagements.
Approach: They propose to develop an annotation tool specifically for developing task-oriented dialogue data that provides comprehensive metadata annotation coverage to the domain, intent, and span information.
Outcome: The tool provides comprehensive metadata annotation coverage to domain, intent, and span information.
CFinBench: A Comprehensive Chinese Financial Benchmark for Large Language Models (2025.naacl-long)

Copied to clipboard

Challenge: Large language models (LLMs) have achieved remarkable performance on various NLP tasks, yet their potential in more challenging task like finance, has not been fully explored.
Approach: They propose a benchmark to assess the financial knowledge of large language models (LLMs) in China.
Outcome: The proposed benchmark is the most comprehensive evaluation benchmark to date for LLMs in finance.

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