Papers by Yawen Wu

6 papers
Towards Multi-label Unknown Intent Detection (2022.coling-1)

Copied to clipboard

Challenge: Existing methods for multi-class unknown intent detection assume that each utterance has only one intent, which is not true because utterrances often contain multiple intents.
Approach: They propose a task to detect whether an utterance contains the unknown intent by recognizing whether all intents contained in the utterant are known.
Outcome: The proposed method significantly reduces the FPR95 on the MultiWOZ 2.3 dataset by 12.25% compared to the best baseline.
On Prefix-tuning for Lightweight Out-of-distribution Detection (2023.acl-long)

Copied to clipboard

Challenge: Out-of-distribution (OOD) detection is a fundamental task vexing real-world applications . fine-tuning based methods require storing fine- tuned models for each scenario .
Approach: They propose an unsupervised prefix-tuning based OOD detection framework called PTO . they propose to take advantage of optional training data labels and targeted OOD data .
Outcome: The proposed framework performs better than existing methods under a wide range of metrics, detection settings, and OOD types.
Debias NLU Datasets via Training-free Perturbations (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing approaches to debiase NLU models capture biased features that are independent of the task but spuriously correlated to labels.
Approach: They propose a framework that conducts training-free perturbations on samples containing biased features to Debias NLU Datasets.
Outcome: The proposed framework shows competitive performance with previous state-of-the-art debiasing strategies.
M2DF: Multi-grained Multi-curriculum Denoising Framework for Multimodal Aspect-based Sentiment Analysis (2023.emnlp-main)

Copied to clipboard

Challenge: Existing work mainly utilizes image information to improve the performance of MABSA task.
Approach: They propose a multimodal Aspect-based Sentiment Analysis task that uses image information to improve model performance.
Outcome: The proposed framework outperforms state-of-the-art work on three sub-tasks of MABSA.
Unlocking Memorization in Large Language Models with Dynamic Soft Prompting (2024.emnlp-main)

Copied to clipboard

Challenge: Pretrained large language models excel in a variety of natural language processing tasks . however, they pose significant security risks due to their tendency to memorize training data .
Approach: They propose a method to estimate LLM memorization using dynamic, prefix-dependent soft prompts.
Outcome: The proposed method can achieve maximum relative improvement of 135.3% and 39.8% over baseline compared to state-of-the-art methods.
SpecAgent: A Speculative Retrieval and Forecasting Agent for Code Completion (2026.acl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) excel at code-related tasks but struggle in real software repositories.
Approach: They propose a large-scale agent that injects repository context at inference time to improve both latency and code-generation quality by proactively exploring repository files during indexing and constructing speculative context.
Outcome: Experiments show that SpecAgent achieves 9–11% relative performance gains compared to baselines while significantly reducing inference latency.

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