Papers by Junzhe Zhang

19 papers
RE-Matching: A Fine-Grained Semantic Matching Method for Zero-Shot Relation Extraction (2023.acl-long)

Copied to clipboard

Challenge: Existing methods for zero-shot relation extraction lack explicit modeling of matching pattern . et al. (2018) show that our method achieves higher matching accuracy and faster inference speed .
Approach: They propose a fine-grained semantic matching method tailored for zero-shot relation extraction . they decompose sentence-level similarity score into entity matching score and context matching score .
Outcome: The proposed method achieves higher matching accuracy and faster inference speed than state-of-the-art methods.
AgentGym2: Benchmarking Large Language Model Agents in De-Idealized Real-World Environments (2026.acl-long)

Copied to clipboard

Challenge: Existing benchmarks evaluate agents in simplified, idealized settings, relying on pre-packaged tool interfaces, overlooking critical steps, and assume inputs are clean and fully specified.
Approach: They propose a framework that evaluates language agents in simplified, idealized settings . they show that even SOTA systems like Gemini and GPT-5 struggle on AgentGym2 .
Outcome: Experiments on 15 proprietary and open-source models show that even SOTA systems like Gemini and GPT-5 struggle on AgentGym2 .
Exploring the Impact of Vision Features in News Image Captioning (2023.findings-acl)

Copied to clipboard

Challenge: Recent state-of-art models can achieve competitive performance even without vision features.
Approach: They conduct extensive experiments with mainstream news image captioning models to determine whether vision features contribute to the generation of captions.
Outcome: The proposed models can achieve competitive performance even without vision features.
PQR: Improving Dense Retrieval via Potential Query Modeling (2025.acl-long)

Copied to clipboard

Challenge: Existing training data is sparse, with each document associated with one or a few labeled queries.
Approach: They propose a training-free potential query retrieval framework to address this problem . they use a Gaussian mixture distribution to model all potential queries for a document .
Outcome: The proposed method is able to capture comprehensive semantic information from a document with multiple queries.
FinMaster: A Holistic Benchmark for Full-Pipeline Financial Management with Large Language Models (2026.findings-acl)

Copied to clipboard

Challenge: Existing benchmarks lack domain-specific data, realistic workflow-level task design, and standardized workflow- level evaluation.
Approach: a new benchmark evaluates large language models on financial management workflows . the global financial services market is projected to grow to $37 trillion by 2027 .
Outcome: a new benchmark for large language models on financial management workflows reveals critical capability gaps . accuracy drops from 90% on basic tasks to 40% on complex scenarios requiring multi-step reasoning . the global financial services market reached $25.8 trillion in 2022 and is projected to grow to $37 trillion by 2027 .
MC-MKE: A Fine-Grained Multimodal Knowledge Editing Benchmark Emphasizing Modality Consistency (2025.findings-acl)

Copied to clipboard

Challenge: Existing benchmarks for knowledge editing in multimodal large language models focus on limited scenarios due to the lack of rigorous definition of multimodal knowledge.
Approach: They propose a decomposed definition of multimodal knowledge and a benchmark to evaluate it.
Outcome: The proposed method reveals that it is difficult to define multimodal knowledge editing in LLMs.
Farewell to Aimless Large-scale Pretraining: Influential Subset Selection for Language Model (2023.findings-acl)

Copied to clipboard

Challenge: Pretrained language models have achieved remarkable success in various natural language processing tasks.
Approach: They propose to use end-task knowledge to select a tiny subset of pretraining corpus to influence performance.
Outcome: The proposed model outperforms pretrained models on eight datasets covering four domains with 0.45% of the data and a three-orders-of-magnitude lower computational cost.
AgentGym: Evaluating and Training Large Language Model-based Agents across Diverse Environments (2025.acl-long)

Copied to clipboard

Challenge: Large language models (LLMs) are promising foundations to build generally-capable agents . however, the community lacks a unified interactive framework that covers diverse environments for comprehensive evaluation of agents.
Approach: They propose a framework that features 7 real-world scenarios, 14 environments, and 89 tasks for unified, real-time, and concurrent agent interaction.
Outcome: The proposed framework features 7 real-world scenarios, 14 environments, and 89 tasks for unified, real-time, and concurrent agent interaction.
Coarse-to-fine Few-shot Learning for Named Entity Recognition (2023.findings-acl)

Copied to clipboard

Challenge: Existing few-shot NER solutions do not consider sub-class discrimination and various granularity of new classes during coarse training.
Approach: They propose a method that uses a cluster-based prototype loss to learn group-wise discriminative representations of coarse-grained classes and a mixture prototype loss for learning the representations.
Outcome: The proposed method shows superior performance over baseline methods on in-domain and cross-domain settings with various target granularity.
Minos: A Multimodal Evaluation Model for Bidirectional Generation Between Image and Text (2026.findings-acl)

Copied to clipboard

Challenge: Existing evaluation models struggle to achieve consistent performance across image-to-text (I2T) and text-to image (T2I) tasks.
Approach: They construct a multimodal evaluation model using a large multimodal dataset and rigorous quality control strategies to train it.
Outcome: The proposed model achieves state-of-the-art evaluation performance across 16 out-of domain datasets covering both I2T and T2I tasks among all open-source multimodal evaluation models and remain competitive with closed-source models.
ARM: An Alignment-and-Replacement Module for Chinese Spelling Check Based on LLMs (2024.emnlp-main)

Copied to clipboard

Challenge: Chinese Spelling Check (CSC) aims to identify and correct spelling errors in Chinese texts, where enhanced semantic understanding of a sentence can significantly improve correction accuracy.
Approach: They propose a plug-and-play Alignment-and -Replacement module that enhances existing Chinese CSC models without retraining or fine-tuning.
Outcome: The proposed module improves existing models while reducing retraining and fine-tuning.
ICR Probe: Tracking Hidden State Dynamics for Reliable Hallucination Detection in LLMs (2025.acl-long)

Copied to clipboard

Challenge: Existing methods for hallucination detection rely on static and isolated representations, overlooking their dynamic evolution across layers.
Approach: They propose a method which captures the cross-layer evolution of hidden states and propose 'ICR Probe' which capture the evolution of the hidden states.
Outcome: The proposed method achieves superior performance with significantly fewer parameters and ablation studies offer deeper insights into the underlying mechanism of the method, improving its interpretability.
LLMEval-Fair: A Large-Scale Longitudinal Study on Robust and Fair Evaluation of Large Language Models (2026.acl-long)

Copied to clipboard

Challenge: Existing evaluation of Large Language Models on static benchmarks is vulnerable to data contamination and leaderboard overfitting.
Approach: LLMEval-Fair framework provides a framework for dynamic evaluation of Large Language Models . evaluators use a proprietary bank of 220k graduate-level questions to analyze model data .
Outcome: LLMEval-Fair provides robust and credible evaluation framework for Large Language Models . it provides a strong empirical validation for the dynamic evaluation paradigm .
Exploring and Evaluating Multimodal Knowledge Reasoning Consistency of Multimodal Large Language Models (2025.findings-emnlp)

Copied to clipboard

Challenge: MLLMs have achieved significant breakthroughs in understanding across text and vision, but current models still face inconsistencies in reasoning outcomes.
Approach: They propose to evaluate multimodal large language models using a multimodal knowledge reasoning dataset to examine the extent of consistency degradation.
Outcome: The proposed evaluation tasks show that MLLMs are inefficient at integrating knowledge across modalities .
Crafting Adversarial Examples for Neural Machine Translation (2021.acl-long)

Copied to clipboard

Challenge: Effective adversary generation for neural machine translation is crucial for robust systems.
Approach: They propose to leverage round-trip translation technique to build valid metrics for evaluating NMT adversarial attacks.
Outcome: The proposed method could break the state-of-art NMT models with small perturbations.
Learning “O” Helps for Learning More: Handling the Unlabeled Entity Problem for Class-incremental NER (2023.acl-long)

Copied to clipboard

Challenge: Existing Named Entity Recognition systems are typically trained on a large-scale dataset with predefined entity classes, then deployed for entity recognition on the test data without further adaptation or refinement.
Approach: They propose a representation learning method that adaptively detects entity clusters in "O" and two effective distance-based relabeling strategies for better learning the old classes.
Outcome: The proposed method achieves 10.62% improvement over the baseline methods.
Enhancing LLM-based Search Agents via Contribution Weighted Group Relative Policy Optimization (2026.acl-long)

Copied to clipboard

Challenge: Existing approaches to training large language models suffer from unstable value estimation, whereas outcome supervision struggles with credit assignment due to sparse, trajectory-level rewards.
Approach: They propose a framework that integrates process supervision into group relative policy optimization.
Outcome: The proposed framework outperforms standard GRPO on knowledge-intensive benchmarks by 5.0% and 6.3% on Qwen3-1.7B.
MM-Doc-R1: Training Agents for Long Document Visual Question Answering through Multi-turn Reinforcement Learning (2026.findings-acl)

Copied to clipboard

Challenge: Existing work on long document visual question answering is based on Retrieval-Augmented Generation (RAG) where textual or visual content is encoded into embeddings and relevance is determined by similarity scores with respect to the original query.
Approach: They propose a framework that employs an agentic, vision-aware workflow to address long document visual question answering through iterative information discovery and synthesis.
Outcome: The proposed framework outperforms existing RL systems by 10.4% on the MMLongbench-Doc benchmark and demonstrates superior training performance over GRPO.
Divide and Conquer: Text Semantic Matching with Disentangled Keywords and Intents (2022.findings-acl)

Copied to clipboard

Challenge: Existing text semantic matching models do not provide granularity for text comparison.
Approach: They propose a simple yet effective training strategy for text semantic matching by disentangling keywords from intents.
Outcome: The proposed approach achieves stable performance improvements against a wide range of models on three benchmarks.

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