Papers by Rongzhi Zhang

11 papers
AcTune: Uncertainty-Based Active Self-Training for Active Fine-Tuning of Pretrained Language Models (2022.naacl-main)

Copied to clipboard

Challenge: Existing methods for fine-tuning pre-trained language models ignore the potential of unlabeled data.
Approach: They propose a framework that allows users to unleash the power of unlabeled data via self-training.
Outcome: The proposed framework outperforms active learning and self-training baselines and improves the label efficiency of PLM fine-tuning by 56.2% on average.
Hephaestus: Improving Fundamental Agent Capabilities of Large Language Models through Continual Pre-Training (2025.naacl-long)

Copied to clipboard

Challenge: Existing LLMs often rely on complex prompting or extensive fine-tuning to introduce new capabilities while preserving strong generalizability.
Approach: They propose a large-scale pre-training corpus to enhance LLM agents' capabilities . they use 103B agent-specific data encompassing 76,537 APIs .
Outcome: The proposed training corpus outperforms open-source LLMs and commercial LLM agents on three agent benchmarks.
Improving Multi-turn Dialogue Modelling with Utterance ReWriter (P19-1)

Copied to clipboard

Challenge: Recent research has achieved impressive results in single-turn dialogue modelling, but multi-turn models still remain challenging.
Approach: They propose to rewrite human utterances as a pre-process to help multi-turn dialgoue modelling.
Outcome: The proposed architecture achieves remarkably good performance on the utterance rewriting task.
ProgGen: Generating Named Entity Recognition Datasets Step-by-step with Self-Reflexive Large Language Models (2024.findings-acl)

Copied to clipboard

Challenge: Large Language Models (LLMs) exhibit remarkable adaptability across domains, but they are often not suitable for structured knowledge extraction tasks such as named entity recognition (NER).
Approach: They propose a method that instructs LLMs to self-reflect on the specific domain and generates domain-relevant attributes for creating attribute-rich training data.
Outcome: The proposed method produces NER datasets in domains with domain-relevant attributes and generates entity terms and NER context data around these entities.
Instant Personalized Large Language Model Adaptation via Hypernetwork (2026.acl-long)

Copied to clipboard

Challenge: Existing parameter-efficient fine-tuning methods require training a separate adapter for each user, making them computationally expensive and impractical for real-time updates.
Approach: They propose a scalable framework that maps a user's profile directly to a full set of adapter parameters.
Outcome: The proposed framework outperforms prompt-based personalization and OPPU while using substantially fewer computational resources at deployment.
Cold-Start Data Selection for Better Few-shot Language Model Fine-tuning: A Prompt-based Uncertainty Propagation Approach (2023.acl-long)

Copied to clipboard

Challenge: Pre-trained language models (PLMs) have achieved competitive performance with limited labeled data for many NLP tasks.
Approach: They propose a prompt-based data selection method for pre-trained language models fine-tuning under cold-start scenarios.
Outcome: The proposed method outperforms the strongest cold-start data selection baselines on six text classification datasets with 128 labels.
DORM: Preference Data Weights Optimization for Reward Modeling in LLM Alignment (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing approaches to align large language models with human preferences are noisy and varying in importance of preference samples.
Approach: a new method enhances reward modeling by learning to dynamically weigh preference data.
Outcome: a new method improves the performance of large language models with human preferences . it initializes data importance and iteratively refines them to maximize validation performance.
PLaD: Preference-based Large Language Model Distillation with Pseudo-Preference Pairs (2024.findings-acl)

Copied to clipboard

Challenge: Knowledge distillation (KD) is a technique for transferring expertise from large teacher models to compact student models with reduced memory footprints and inference costs.
Approach: They propose to transfer knowledge from large teacher models to compact student models by exploiting teacher-student capacity discrepancies to generate pseudo-preference pairs where teacher outputs are preferred over student outputs.
Outcome: The proposed framework exploits teacher-student capacity discrepancy to generate pseudo-preference pairs where teacher outputs are preferred over student outputs.
ReGen: Zero-Shot Text Classification via Training Data Generation with Progressive Dense Retrieval (2023.findings-acl)

Copied to clipboard

Challenge: Recent studies show that large pretrained language models can generate training data with no task-specific or cross-task data.
Approach: They propose a retrieval-enhanced framework to create training data from a general-domain unlabeled corpus.
Outcome: The proposed framework achieves 4.3% gain over baselines and saves 70% of time compared with baselines using large language models.
Prompt-Based Rule Discovery and Boosting for Interactive Weakly-Supervised Learning (2022.acl-long)

Copied to clipboard

Challenge: Weakly-supervised learning (WSL) has shown promising results in addressing label scarcity on many NLP tasks, but manual designing a comprehensive, high-quality set of labeling rules is tedious and difficult.
Approach: They propose a weakly-supervised learning model that iterates and discovers new labeling rules from data to improve the WSL model.
Outcome: The proposed model outperforms state-of-the-art models on four tasks and bridges the gaps with fully supervised models.
SeqMix: Augmenting Active Sequence Labeling via Sequence Mixup (2020.emnlp-main)

Copied to clipboard

Challenge: Existing active sequence labeling methods use the queried samples alone in each iteration, which is inefficient for leveraging human annotations.
Approach: They propose a data augmentation method to augment queried samples by generating extra labeled sequences in each iteration.
Outcome: The proposed method improves the standard active sequence labeling method by 2.27%–3.75% in terms of F1 scores.

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