Papers by Qianhui Wu

12 papers
LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Models (2023.emnlp-main)

Copied to clipboard

Challenge: Large language models (LLMs) are increasingly lengthy and require longer prompts . this paper presents a coarse-to-fine prompt compression method to reduce cost and increase performance.
Approach: They propose a coarse-to-fine prompt compression method that maintains semantic integrity under high compression ratios and a token-level iterative compression algorithm to better model the interdependence between compressed contents.
Outcome: The proposed method yields state-of-the-art performance and allows for up to 20x compression with little performance loss over four datasets from different scenarios.
Multi-Level Knowledge Distillation for Out-of-Distribution Detection in Text (2023.acl-long)

Copied to clipboard

Challenge: Self-supervised representation learning has proved to be a valuable component for out-of-distribution (OoD) detection with only the texts of in-difference (ID) examples.
Approach: They propose a method that integrates strengths and weaknesses of both methods . they use a fine-tuned model as the teacher to teach a randomly initialized student model .
Outcome: The proposed method outperforms human evaluators in the pair-expert task on the Human ChatGPT Comparison Corpus.
Mitigate Position Bias in LLMs via Scaling a Single Hidden States Channel (2025.findings-acl)

Copied to clipboard

Challenge: Long-context language models exhibit position bias, also known as "lost in the middle" research shows that even long-contemporary LLMs fail to utilize all context information effectively .
Approach: They propose a method to mitigate position bias by scaling positional hidden states . they propose to use a channel of hidden states to modify positional Hidden states a LCLM's positional bias .
Outcome: The proposed method can improve performance by 15.2% in a "lost in the middle" benchmark.
TACO-RL: Task Aware Prompt Compression Optimization with Reinforcement Learning (2025.findings-acl)

Copied to clipboard

Challenge: Existing prompt compression techniques rely on sub-optimal metrics such as information entropy or model it as a task-agnostic token classification problem that fails to capture task-specific information.
Approach: They propose a task-aware prompt compression method that leverages existing Transformer encoders and a lightweight REINFORCE algorithm to ensure low latency requirements.
Outcome: The proposed method improves task performance by 8% - 189% on three diverse and challenging tasks over state-of-the-art techniques while satisfying the same compression rate and latency requirements.
On the Effectiveness of Sentence Encoding for Intent Detection Meta-Learning (2022.naacl-main)

Copied to clipboard

Challenge: Recent studies on few-shot intent detection have attempted to formulate the task as a meta-learning problem.
Approach: They propose to modify a few-shot intent detection task to produce a non-trivially strong performance without further domain-specific adaptation.
Outcome: The proposed model improves on the prototypical network variants with task-specific fine-tuning.
CoLaDa: A Collaborative Label Denoising Framework for Cross-lingual Named Entity Recognition (2023.acl-long)

Copied to clipboard

Challenge: Existing approaches to named entity recognition (NER) are limited by the cost of labeling and labeling, especially for low-resource languages.
Approach: They propose a model-collaboration-based denoising scheme that enables models trained on different data sources to collaboratively denoise pseudo labels used by each other.
Outcome: The proposed framework achieves superior results on benchmark datasets and can generalize to distant languages.
Decomposed Meta-Learning for Few-Shot Named Entity Recognition (2022.findings-acl)

Copied to clipboard

Challenge: Named entity recognition systems aim at recognizing unseen entity types based on a few labeled examples.
Approach: They propose a decomposed meta-learning approach to solve few-shot span detection and few- shot entity typing problems by introducing a model-agnostic meta-loop algorithm.
Outcome: The proposed approach achieves superior performance over prior methods on benchmarks.
Single-/Multi-Source Cross-Lingual NER via Teacher-Student Learning on Unlabeled Data in Target Language (2020.acl-main)

Copied to clipboard

Challenge: Existing approaches to named entity recognition (NER) are limited by label projection with pairwise texts or direct model transfer.
Approach: They propose a method where NER models in the source languages are used as teachers to train a student model on unlabeled data in the target language.
Outcome: The proposed method outperforms existing state-of-the-art methods for single-source and multi-source cross-lingual NER on target languages.
SynthAgent: Adapting Web Agents with Synthetic Supervision (2026.acl-long)

Copied to clipboard

Challenge: Existing studies have focused on synthetic supervision but have encountered data quality issues.
Approach: They propose a fully synthetic supervision framework that aims at improving data quality via dual refinement of both tasks and trajectories.
Outcome: The proposed framework outperforms existing methods on standardized benchmarks and shows promising results on a standardized test.
LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression (2024.findings-acl)

Copied to clipboard

Challenge: Existing approaches to compress prompts only leverage unidirectional context, causing suboptimal results.
Approach: They propose a task-agnostic prompt compression method that takes tokens from context . they use a Transformer encoder to capture all essential information needed for prompt compression .
Outcome: The proposed method is 3x-6x faster than existing prompt compression methods and faster than baselines.
AdvPicker: Effectively Leveraging Unlabeled Data via Adversarial Discriminator for Cross-Lingual NER (2021.acl-long)

Copied to clipboard

Challenge: Named entity recognition models rely on expensive labeled data for training, which is not always available across languages.
Approach: They propose an adversarial approach where an encoder learns entity domain knowledge from labeled source-language data and better shared features are captured via adversarially trained discriminators.
Outcome: The proposed approach outperforms existing state-of-the-art methods on standard benchmark datasets and outperformed existing methods on the target language.
LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression (2024.acl-long)

Copied to clipboard

Challenge: Longer prompts introduce irrelevant and redundant information, which can weaken LLMs' performance.
Approach: They propose a prompt compression tool that improves LLMs' perception of key information in input prompts by up to 21.4% with around 4x fewer tokens in GPT-3.5-Turbo.
Outcome: The proposed solution improves performance and reduces costs and latency by up to 21.4% with around 4x fewer tokens in the NaturalQuestions benchmark.

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