Papers by Zhengxin Zhang

6 papers
Better LLM Reasoning via Dual-Play (2026.findings-acl)

Copied to clipboard

Challenge: Large Language Models (LLMs) have made remarkable progress through Reinforcement Learning with Verifiable Rewards (RLVR) however, external supervision remains a bottleneck for tasks and domains for which supervised data are scarce or non-existent.
Approach: They propose a novel dual-play framework that adversarially trains two models initialized from the same base model.
Outcome: The proposed framework improves the math reasoning performance of large language models.
GSM-Noise: Exploring and Enhancing Large Language Models’ Reasoning under Noisy Inputs (2026.findings-acl)

Copied to clipboard

Challenge: Large language models struggle when dealing with complex, ill-formed, or noisy inputs . open-source models are less robust, while closed-source ones are more robust .
Approach: They propose to use GSM-Noise to refine inputs before engaging in in-depth analysis to improve LLM robustness under noisy conditions.
Outcome: The proposed model can achieve consistent performance gains under noisy conditions with prompt engineering, supervised finetuning, and reinforcement learning.
CAPC-CG: A Large-Scale, Expert-Directed LLM-Annotated Corpus of Adaptive Policy Communication in China (2026.acl-long)

Copied to clipboard

Challenge: Adaptive policy communication is a theory of governance in large, decentralized organizations where leaders exercise influence rather than precise control by combining clear and ambiguous instructions to calibrate discipline and flexibility.
Approach: They propose an expert-directed annotation method that integrates codebook design, structured training, a two-step workflow, and LLM-based scaling.
Outcome: The proposed method achieves a Fleiss’ kappa of 0.86 on directive labels, indicating high reliability.
Enhancing Context Modeling with a Query-Guided Capsule Network for Document-level Translation (D19-1)

Copied to clipboard

Challenge: Context modeling is essential to generate coherent and consistent translation for document-level Neural Machine Translations.
Approach: They propose a query-guided capsule network to cluster context information into different perspectives from which the target translation may concern.
Outcome: The proposed model outperforms baseline models on multiple datasets of different domains.
Quantized Side Tuning: Fast and Memory-Efficient Tuning of Quantized Large Language Models (2024.acl-long)

Copied to clipboard

Challenge: Existing methods to finetun large language models (LLMs) only update a small number of trainable parameters, or attempt to reduce the memory footprint during the training phase of the finetune process.
Approach: They propose quantized side tuing (QST) which quantizes an LLM’s model weights into 4-bit to reduce the memory footprint of the original weights.
Outcome: The proposed method reduces the memory footprint of the model weights, optimizer states, and intermediate activations while reducing the memory requirements.
Alleviating Performance Degradation Caused by Out-of-Distribution Issues in Embedding-Based Retrieval (2025.findings-emnlp)

Copied to clipboard

Challenge: Recent studies reveal query out-of-distribution issues degrading ANN performance . a distribution regularizer is introduced into the encoder training objective to encourage alignment between query and base embeddings.
Approach: They introduce a distribution regularizer into the encoder training objective to encourage alignment between query and base embeddings.
Outcome: The proposed method consistently improves retrieval performance across multiple datasets.

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