Papers by Wei Pang

19 papers
MoNMT: Modularly Leveraging Monolingual and Bilingual Knowledge for Neural Machine Translation (2024.lrec-main)

Copied to clipboard

Challenge: Existing models for multi-domain translation tasks only use monolingual data, whereas bilingual data is indispensable for improving the models.
Approach: They propose a modular strategy that facilitates the cooperation of monolingual and bilingual knowledge in translation tasks by avoiding catastrophic forgetting.
Outcome: The proposed model exhibits superior generalization and robustness over the conventional approach.
MERMAID: Multi-perspective Self-reflective Agents with Generative Augmentation for Emotion Recognition (2025.emnlp-main)

Copied to clipboard

Challenge: Existing multimodal large language models struggle to handle ambiguous emotional expressions and implicit affective cues, which are crucial for affective understanding but largely overlooked.
Approach: They propose a multi-agent framework that integrates a self-reflection module, an emotion-guided visual augmentation module, and a cross-modal verification module to enhance emotion recognition.
Outcome: Extensive experiments show that MERMAID outperforms existing methods and achieves absolute accuracy gains of 8.70%–27.90% across diverse benchmarks.
SharedRequest: Privacy-Preserving Model-Agnostic Inference for Large Language Models (2026.acl-long)

Copied to clipboard

Challenge: Existing privacy-preserving inference methods sacrifice utility or efficiency, authors say . current approaches suffer a trilemma between privacy, utility, and efficiency, they say .
Approach: They propose a model-agnostic framework for privacy-preserving LLM inference that reformulates privacy protection at the batch level rather than the individual-prompt level.
Outcome: The proposed model-agnostic framework achieves 20% higher utility than previous models . it reduces query cost by up to 5 compared to non-batched inference .
MLaKE: Multilingual Knowledge Editing Benchmark for Large Language Models (2025.coling-main)

Copied to clipboard

Challenge: Existing studies on knowledge editing focus on monolingual scenarios, neglecting the complexities presented by multilingual contexts and multi-hop reasoning.
Approach: They propose a benchmark to evaluate the adaptability of multilingual knowledge editing methods.
Outcome: The proposed benchmark evaluates the adaptability of multilingual knowledge editing methods across five languages.
Self-Distillation Bridges Distribution Gap in Language Model Fine-Tuning (2024.acl-long)

Copied to clipboard

Challenge: Experimental results show that fine-tuning of large language models for specific tasks can be challenging . distribution shift during fine-timing can lead to performance degradation in general task capabilities .
Approach: They propose a new approach that bridges the distribution gap between task datasets and LLMs by guiding fine-tuning with a distilled dataset generated by the model itself.
Outcome: The proposed approach achieves comparable or superior performance on downstream tasks compared to the vanilla approach.
HierPrompt: Zero-Shot Hierarchical Text Classification with LLM-Enhanced Prototypes (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for Hierarchical Text Classification are based on prototypes, but do not perform well due to ambiguity and impreciseness of category names.
Approach: They propose a method that leverages hierarchy-aware prompts to instruct LLM to produce more representative and informative prototypes.
Outcome: The proposed method outperforms existing methods on three benchmark datasets.
DREAM: Improving Video-Text Retrieval Through Relevance-Based Augmentation Using Large Foundation Models (2025.naacl-long)

Copied to clipboard

Challenge: Recent advances in video-text retrieval models have limited training data annotations.
Approach: They propose a Video-Text Retrieval Paradigm with Relevance-based Augmentation which enhances video and text data using large foundation models to learn more generalized features.
Outcome: The proposed method improves video-text retrieval performance over existing methods.
ToolCoder: A Systematic Code-Empowered Tool Learning Framework for Large Language Models (2025.acl-long)

Copied to clipboard

Challenge: Existing approaches to tool learning rely on hand-crafted prompts and natural language reasoning, making multi-step planning difficult and lacking precise error diagnosis and reflection mechanisms.
Approach: They propose a framework that reformulates tool learning as a code generation task.
Outcome: The proposed framework achieves superior performance in task completion accuracy and execution reliability compared to existing approaches.
Breaking the Evaluation Paradox: Evaluating High-Entropy Search with Computationally Irreducible Constraints (2026.findings-acl)

Copied to clipboard

Challenge: a new framework for evaluation of exhaustive search capabilities is needed . high-entropy enumeration tasks make such ground truth impossible for humans to create . VERITAS is a framework built on the principle of computationally irreducible constraints .
Approach: They propose a framework that uses non-optimizable constraints to create verifiable searches . VERITAS can generate infinite number of test cases with perfect ground truth and precise difficulty control .
Outcome: a new evaluation framework for large language models is based on non-optimizable constraints . the framework can generate infinite number of test cases with perfect ground truth and precise difficulty control .
Mitigating Over-Refusal in Aligned Large Language Models via Inference-Time Activation Energy (2026.acl-long)

Copied to clipboard

Challenge: Existing safety alignment techniques prioritize mitigating harmful responses at the expense of overcautious behavior, leading models to incorrectly refuse benign requests.
Approach: They propose a fine-tuning free framework to improve safety and reduce false refusals by dynamic, inference-time intervention.
Outcome: The proposed framework raises compliance on the ORB-H benchmark from 57.3% to 82.6% while maintaining the baseline safety performance.
MacLaSa: Multi-Aspect Controllable Text Generation via Efficient Sampling from Compact Latent Space (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing approaches to multi-aspect controllable text generation require expensive iteration / searching within the discrete text space during the decoding stage, resulting in a degradation of text quality due to the domain discrepancies between different aspects.
Approach: They propose a framework that estimates compact latent space for multiple aspects and performs efficient Sampling with a fast sampler to eliminate domain discrepancies.
Outcome: The proposed framework outperforms baselines on attribute relevance and textual quality while maintaining a high inference speed.
OFFSIDE: Benchmarking Unlearning Misinformation in Multimodal Large Language Models (2026.findings-acl)

Copied to clipboard

Challenge: Existing benchmarks for MU are limited by a lack of image diversity and coarse-grained unlearning targets.
Approach: They propose a benchmark to evaluate misinformation unlearning in MLLMs . OFFSIDE supports advanced unlearning targets such as fine-grained unlearning and visual rumor removal.
Outcome: OFFSIDE supports advanced unlearning targets, such as fine-grained unlearning and visual rumor removal.
Phased Instruction Fine-Tuning for Large Language Models (2024.findings-acl)

Copied to clipboard

Challenge: Existing methods to enhance pre-trained language models' ability to follow instructions are limited due to the simultaneous handling of varying instruction complexities.
Approach: They propose a phased instruction fine-tuning method that posits that the transition of a pre-trained language model from simple next-word prediction to sophisticated instruction following is a gradual learning process.
Outcome: The proposed method surpasses the one-off instruction fine-tuning method in win rate and validates the hypothesis of progressive alignment.
The Evolution of Thought: Tracking LLM Overthinking via Reasoning Dynamics Analysis (2026.acl-long)

Copied to clipboard

Challenge: Explicit reasoning trajectories increase performance but often trigger overthinking . despite its importance, this study examines how each step of reasoning affects the final outcome .
Approach: They propose a Reasoning Completion Point Detector that detects the RCP by monitoring rank dynamics of termination tokens.
Outcome: The proposed method reduces token usage by up to 44% while preserving accuracy.
Following the Autoregressive Nature of LLM Embeddings via Compression and Alignment (2025.emnlp-main)

Copied to clipboard

Challenge: Experimental results demonstrate that our method significantly outperforms traditional contrastive learning approaches when using the same amount of data.
Approach: They propose a new contrastive learning method built on embedding conditional probability distributions that integrates two tasks: information compression and conditional distribution alignment.
Outcome: The proposed method outperforms traditional contrastive learning approaches and achieves comparable performance to state-of-the-art models when using the same amount of data.
TextFlint: Unified Multilingual Robustness Evaluation Toolkit for Natural Language Processing (2021.acl-demo)

Copied to clipboard

Challenge: Existing approaches to textual robustness evaluation focus on slightly modifying the input data, which maintains the original meaning and results in a different prediction.
Approach: They propose a multilingual robustness evaluation toolkit for NLP that integrates universal text transformations, task-specific transformations and adversarial attack.
Outcome: The toolkit includes universal text transformation, task-specific transformation, adversarial attack, subpopulation, and their combinations to provide comprehensive robustness analyses.
Privacy-Preserving Reasoning with Knowledge-Distilled Parametric Retrieval Augmented Generation (2026.findings-acl)

Copied to clipboard

Challenge: Existing RAG systems require uploading local documents to the cloud, resulting in inference latency and poor generalization on out-of-distribution (OOD) inputs.
Approach: They propose a generalizable knowledge-distilled parametric RAG model aligned with standard RAG in document structure and parameter activation.
Outcome: The proposed model outperforms baselines in accuracy and generalizes well on out-of-distribution (OOD) data.
Monotonic Infinite Lookback Attention for Simultaneous Machine Translation (P19-1)

Copied to clipboard

Challenge: Simultaneous machine translation begins to translate each source sentence before the source speaker has finished speaking, with applications to live and streaming scenarios.
Approach: They propose a simultaneous translation system that learns an adaptive schedule with a neural machine translation model that attends over all source tokens read thus far.
Outcome: The proposed system can achieve latency-quality trade-offs favorable to a proposed wait-k strategy for many latency values.
Multimodal Misinformation Detection by Learning from Synthetic Data with Multimodal LLMs (2024.findings-emnlp)

Copied to clipboard

Challenge: Obtaining large-scale, high-quality real-world fact-checking datasets is costly . generalizability of detectors trained on synthetic data to real-life scenarios remains unclear .
Approach: They propose to use synthetic data to learn from real-world data to detect multimodal misinformation . they propose to combine model-agnostic data selection methods with real-life data distributions .
Outcome: The proposed method improves the performance of a small MLLM on real-world fact-checking datasets, surpassing GPT-4V.

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