Papers by Zhiyuan Ji

13 papers
Graph-GRPO: Stabilizing Multi-Agent Topology Learning via Group Relative Policy Optimization (2026.findings-acl)

Copied to clipboard

Challenge: Recent approaches to optimize communication topology rely on single-sample policy gradients with absolute rewards.
Approach: They propose a topology optimization framework that integrates Group Relative Policy Optimization.
Outcome: The proposed topology optimization framework outperforms state-of-the-art methods on reasoning and code generation benchmarks.
Denoising Distantly Supervised Open-Domain Question Answering (P18-1)

Copied to clipboard

Challenge: Existing DS-QA models ignore rich information contained in other paragraphs and are noisy . Existing systems rely on pre-identified relevant texts, which do not always exist in real-world QA scenarios.
Approach: They propose a model which uses a paragraph selector to filter out noisy paragraphs and a reader to extract the correct answer from denoised paragraphs.
Outcome: The proposed model can capture useful information from noisy data and achieve significant improvements on open domain question answering.
Emergent Relational Order in LLM Agent Societies: From Collective Affect to Authority Stratification (2026.findings-acl)

Copied to clipboard

Challenge: Fei Xiaotong’s Differential Order Pattern characterizes rural society as egocentric and relationally graded, with cooperation attenuating over social distance.
Approach: They propose a multi-agent framework grounded in Affect Control Theory, Social Identity Theory, and Durkheimian collective affect.
Outcome: Extensive simulations support interpreting Differential Order as a structure-sensitive emergent outcome of general social mechanisms.
From Adversarial Arms Race to Model-centric Evaluation: Motivating a Unified Automatic Robustness Evaluation Framework (2023.findings-acl)

Copied to clipboard

Challenge: Existing models of robustness evaluation are incomprehensive, impractical, and invalid .
Approach: They propose a framework for automatic robustness evaluation that shifts towards model-centric evaluation to further exploit the advantages of adversarial attacks.
Outcome: The proposed framework is based on a model-centric evaluation protocol and a robustness evaluation protocol.
PEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language Models (2022.emnlp-main)

Copied to clipboard

Challenge: Recent advances on self-supervised learning have led to powerful vision-language pre-training models that achieve state-of-the-art performance on a wide range of cross-modal tasks.
Approach: They propose a vision-language pre-training framework that reformulates discretized object positions and language in a unified language modeling framework.
Outcome: The proposed model improves performance on position-sensitive vision-language (VL) tasks and also improves on position insensitive tasks.
Low-Resource Name Tagging Learned with Weakly Labeled Data (D19-1)

Copied to clipboard

Challenge: Existing methods for name tagging in low-resource languages or domains require extensive human efforts for training annotations.
Approach: They propose a neural model for name tagging based on weakly labeled (WL) data.
Outcome: The proposed model outperforms existing models in five low-resource languages and fine-grained food domains and shows that it is more efficient and efficient than existing models.
A Close Look into the Calibration of Pre-trained Language Models (2023.acl-long)

Copied to clipboard

Challenge: Pre-trained language models (PLMs) may fail in giving reliable estimates of their predictive uncertainty.
Approach: They conduct fine-grained control experiments to study the dynamic change in PLMs’ calibration performance in training.
Outcome: The proposed methods significantly reduce PLMs’ confidence in wrong predictions.
MoC: Mixtures of Text Chunking Learners for Retrieval-Augmented Generation System (2025.acl-long)

Copied to clipboard

Challenge: Existing methods for text chunking are limited by text chunks and lack of domain-specific knowledge.
Approach: They propose a dual-metric evaluation method to quantify text chunking quality . they aim to generate a structured list of chunking regular expressions .
Outcome: The proposed method enables direct quantification of chunking quality . it substantiates the need to integrate LLMs into chunking process .
CALM: Unleashing the Cross-Lingual Self-Aligning Ability of Language Model Question Answering (2025.findings-naacl)

Copied to clipboard

Challenge: Large Language Models (LLMs) are pre-trained on extensive multilingual corpora to acquire both language-specific cultural knowledge and general knowledge.
Approach: They propose to use the **C**ross-Lingual Self-**Aligning ability of **L**anguage **M**odels to align knowledge across languages.
Outcome: The proposed model performs well in both zero-shot and retrieval-augmented settings.
ERICA: Improving Entity and Relation Understanding for Pre-trained Language Models via Contrastive Learning (2021.acl-long)

Copied to clipboard

Challenge: Existing pre-training objectives do not explicitly model relational facts in text . Experimental results show that ERICA can improve typical PLMs on several language understanding tasks, including relation extraction, entity typing and question answering.
Approach: They propose a contrastive learning framework ERICA to obtain a deep understanding of entities and relations in text.
Outcome: The proposed framework can improve PLMs on several language understanding tasks, especially under low-resource settings.
Put It Back: Entity Typing with Language Model Enhancement (D18-1)

Copied to clipboard

Challenge: Existing Entity typing models suffer from noisy labels due to distant supervision .
Approach: They propose to enhance existing entity typing models with language model enhancement to measure compatibility between context sentences and labels.
Outcome: The proposed model significantly outperforms the state-of-the-art model on benchmark datasets and is available on github.
Building an Ellipsis-aware Chinese Dependency Treebank for Web Text (L18-1)

Copied to clipboard

Challenge: ellipsis is a common linguistic phenomenon that some words are left out as they are understood from the context, especially in oral utterance.
Approach: They propose to use a Chinese dependency treebank to facilitate the parsing of web text . they propose to restore omissions and reserve contexts in the web text to improve dependency parsers .
Outcome: The proposed framework enables the parsing of web text from online microblogs.
CREATOR: Tool Creation for Disentangling Abstract and Concrete Reasoning of Large Language Models (2023.findings-emnlp)

Copied to clipboard

Challenge: Large Language Models (LLMs) have made significant progress in utilizing tools, but their ability is limited by API availability and the instability of implicit reasoning.
Approach: They propose a framework that enables LLMs to create their own tools using documentation and code realization.
Outcome: The proposed framework outperforms existing chain-of-thought, program-of thought, and tool-using baselines on MATH and TabMWP 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