Papers by Junzhe Chen

13 papers
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 .
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.
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.
Teaching LLMs to Plan, Not Just Solve: Plan Learning Boosts LLMs Generalization in Reasoning Tasks (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for reinforcement learning (RL) on self-generated data are limited in many domains.
Approach: a new framework combines plan-based search with Step-level Advantage Preference Optimization to optimize plan learning.
Outcome: The proposed framework improves in-domain performance and out-of-domain benchmarks.
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.
AED-RAG: Continuous Multi-Granular Context Fusion for Retrieval-Augmented Generation via Adaptive Ensemble Decoding (2026.findings-acl)

Copied to clipboard

Challenge: Existing alignment strategies that rely on discrete reranking struggle to address this granularity mismatch or effectively balance external evidence with internal knowledge.
Approach: They propose a framework that synergizes discrete retrieval with continuous reranking to discern the information density differences between unstructured narrative passages and structured knowledge triplets.
Outcome: Extensive experiments on four open-domain QA benchmarks show that AED-RAG significantly outperforms competitive baselines.
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.
LLMArena: Assessing Capabilities of Large Language Models in Dynamic Multi-Agent Environments (2024.acl-long)

Copied to clipboard

Challenge: Existing benchmarks for evaluating large language models use static datasets, leading to data leakage or overlooking the complexities of multi-agent interactions.
Approach: They propose a framework that evaluates the diverse capabilities of LLM agents in multi-agent dynamic environments.
Outcome: The proposed framework assesses the diverse capabilities of LLM agents in multi-agent dynamic environments.
Evaluating Robustness of Generative Search Engine on Adversarial Factoid Questions (2024.findings-acl)

Copied to clipboard

Challenge: Existing large language models (LLMs)-backed generative search engines may not always be accurate.
Approach: They propose to evaluate the robustness of retrieval-augmented generation in a realistic and high-risk setting where adversaries have only black-box system access.
Outcome: The proposed model exhibits higher susceptibility to factual errors compared to LLMs without retrieval.
MHALO: Evaluating MLLMs as Fine-grained Hallucination Detectors (2025.findings-acl)

Copied to clipboard

Challenge: Hallucination remains a critical challenge for multimodal large language models, undermining their reliability in real-world applications.
Approach: They propose a benchmark specifically designed for evaluating MLLMs’ capability in performing token-level hallucination detection (FHD) . they use curated training data to train a specialized model that significantly outperforms existing models.
Outcome: The proposed model outperforms existing models in the evaluation of 9 MLLMs and reaches an average F1IoU of 40.59%.

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