Papers by Huijia Zhu

13 papers
Probe Then Retrieve and Reason: Distilling Probing and Reasoning Capabilities into Smaller Language Models (2024.lrec-main)

Copied to clipboard

Challenge: Recent research efforts have focused on distilling Large Language Models into Small Language Model (SLMs) however, the results of CoT distillation are inadequate for knowledge-intensive reasoning tasks.
Approach: They propose a retrieval-based framework which distills question probing and reasoning capabilities from Large Language Models into SLMs.
Outcome: The proposed framework improves probing and reasoning capabilities of large language models in knowledge-intensive reasoning tasks.
TransAdv: A Translation-based Adversarial Learning Framework for Zero-Resource Cross-Lingual Named Entity Recognition (2022.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for named entity recognition are limited by noise in translation . Existing approaches to named entities recognition are mainly based on labeled data .
Approach: They propose a framework to mitigate lexical and syntactic errors of translated data . they propose to use multi-level adversarial learning and multi-model knowledge distillation to mitigate noise .
Outcome: The proposed framework mitigates lexical and syntactic errors of translated data . it achieves competitive performance to state-of-the-art models .
Reading Order Matters: Information Extraction from Visually-rich Documents by Token Path Prediction (2023.emnlp-main)

Copied to clipboard

Challenge: Recent advances in multimodal pre-trained models have significantly improved information extraction from visually-rich documents (VrDs).
Approach: They propose a method to predict token sequences within visually-rich documents by a simple prediction head.
Outcome: The proposed method can be used to predict token mentions as token sequences within documents.
Beyond Full Fine-tuning: Harnessing the Power of LoRA for Multi-Task Instruction Tuning (2024.lrec-main)

Copied to clipboard

Challenge: Low-Rank Adaptation (LoRA) is a parameter-efficient fine-tuning algorithm for large-scale language models.
Approach: They conduct a systematic study of Low-Rank Adaptation (LoRA) on diverse tasks and rich resources with different learning capacities.
Outcome: The proposed algorithm can achieve remarkable performance in high-resource and multi-task scenarios, even comparable to full fine-tuning.
Aligning Retrieval with Reader Needs: Reader-Centered Passage Selection for Open-Domain Question Answering (2025.coling-main)

Copied to clipboard

Challenge: Existing retrieval methods aim to gather relevant passages but fail to prioritize consistent and useful information for the reader.
Approach: They propose a novel method which re-ranks passages based on the reader's prediction probability distribution and clusters passage according to the predicted answers.
Outcome: The proposed method improves the quality of evidence passages under zero-shot scenarios.
XMC-Agent : Dynamic Navigation over Scalable Hierarchical Index for Incremental Extreme Multi-label Classification (2024.findings-acl)

Copied to clipboard

Challenge: Existing methods for XMC struggle with the growing set of labels due to their static label assumptions, and embedding-based methods struggle with complex mapping relationships due to late interaction paradigm.
Approach: They propose a large language model (LLM) powered agent framework for extreme multi-label classification, XMC-Agent, which can effectively learn, manage and predict the extremely large and dynamically increasing set of labels.
Outcome: The proposed framework can learn, manage and predict the extremely large and dynamically growing set of labels and achieves state-of-the-art performance on three standard datasets.
Debiasing In-Context Learning by Instructing LLMs How to Follow Demonstrations (2024.findings-acl)

Copied to clipboard

Challenge: In-context learning (ICL) has gained considerable attention due to its data efficiency and task adaptability.
Approach: They propose to de-biase demonstration bias in in-context learning by focusing on semantic ambiguity induced by demonstrations and reducing the semantic hazard.
Outcome: The proposed methods significantly improve performance on six datasets.
A Multi-Task Dual-Tree Network for Aspect Sentiment Triplet Extraction (2022.coling-1)

Copied to clipboard

Challenge: Existing methods are poor at detecting complicated relations between aspects and opinions . detecting unclear boundaries of multi-word aspects and opinion is also a challenge .
Approach: They propose a multi-task dual-tree network to extract triplets from a given sentence . they employ a constituency tree and a modified dependency tree to enhance the interaction .
Outcome: The proposed model extracts triplets from a given sentence, and it is effective on four datasets.
Modeling Layout Reading Order as Ordering Relations for Visually-rich Document Understanding (2024.emnlp-main)

Copied to clipboard

Challenge: Existing models of layout reading order do not convey the complete reading order information in the layout.
Approach: They propose to model layout reading order as ordering relations over layout elements . they propose a reading-order-relation-enhancing pipeline to improve model performance .
Outcome: The proposed model outperforms existing models on a visual-rich document dataset and on eight cross-domain VrD-IE/QA tasks without targeted optimization.
CrisPrune: Combining Contextual Relevance and Intrinsic Saliency for Efficient Visual Token Pruning in MLLMs (2026.findings-acl)

Copied to clipboard

Challenge: Existing methods for visual token pruning compromise the integrity of visual understanding in pursuit of efficiency.
Approach: They propose a model-agnostic method that integrates visual saliency and text relevance to reconcile efficiency with understanding by integrating visual salions and text relevant.
Outcome: The proposed method outperforms state-of-the-art methods on LLaVA-NeXT . it achieves 13 decrease in FLOPs while maintaining 97% of original performance .
Chain-of-Rewrite: Aligning Question and Documents for Open-Domain Question Answering (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing approaches to answer open-domain question have encountered term mismatch and limited interaction between IR systems and large language models.
Approach: They propose a method which leverages the guidance and feedback gained from the analysis to provide faithful and consistent extensions for effective question answering.
Outcome: Experiments on four open-domain question answering datasets show the proposed method performs well under zero-shot settings.
Sparse Latents Steer Retrieval-Augmented Generation (2025.acl-long)

Copied to clipboard

Challenge: In this study, we uncover interpretable latents that govern RAG behavior in large language models . Sparse Autoencoders are used to control large language model (LLM) behavior .
Approach: They leverage Sparse Autoencoders within the LLaMA Scope to uncover latents that govern RAG behaviors.
Outcome: The proposed model can be used to control large language models without architectural modifications.
SpeechFake: A Large-Scale Multilingual Speech Deepfake Dataset Incorporating Cutting-Edge Generation Methods (2025.acl-long)

Copied to clipboard

Challenge: Existing speech deepfake datasets are limited in scale and diversity, making it challenging to train models that can generalize well to unseen deepfakkes.
Approach: They propose a large-scale speech deepfake dataset that includes over 3 million deepfak samples, totaling more than 3,000 hours of audio, generated using 40 different speech synthesis tools.
Outcome: The proposed dataset includes over 3 million deepfake samples, totaling more than 3,000 hours of audio, generated using 40 different speech synthesis tools.

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