Papers by Chenghao Sun

9 papers
Reference Network for Neural Machine Translation (P19-1)

Copied to clipboard

Challenge: Neural Machine Translation (NMT) generates translations in isolation, resulting in translation inconsistency and ambiguity.
Approach: They propose to incorporate referring process into translation decoding of NMT by using local coordinates coding to obtain global context vectors containing monolingual and bilingual contextual information.
Outcome: The proposed model improves translation quality with lightweight computation cost on Chinese-English and English-German translation tasks.
Heterogeneous Graph Neural Networks for Concept Prerequisite Relation Learning in Educational Data (2021.naacl-main)

Copied to clipboard

Challenge: Existing methods to learn prerequisite relations among concepts are lacking . concepts are crucial for learning, organizing, applying and generating knowledge .
Approach: They propose a concept prerequisite relation learning approach which combines concept representation and concept pairwise features to make it more practical.
Outcome: The proposed method achieves state-of-the-art results on four datasets.
ReasonMed: A 370K Multi-Agent Generated Dataset for Advancing Medical Reasoning (2025.emnlp-main)

Copied to clipboard

Challenge: Existing medical reasoning datasets are limited in scale and typically rely on incomplete data.
Approach: They propose to use ReasonMed to train medical reasoning models using a multi-agent generation, verification, and refinement pipeline.
Outcome: The largest medical reasoning dataset to date surpasses the prior best sub-10B models by 4.17% and even exceeds LLaMA3.1-70B on PubMedQA by 4.60%.
Word-level Textual Adversarial Attacking as Combinatorial Optimization (2020.acl-main)

Copied to clipboard

Challenge: Existing word-level attack models are far from perfect because of unsuitable search space reduction methods and inefficient optimization algorithms.
Approach: They propose a novel adversarial adversarialist model that incorporates word substitution and particle swarm optimization to solve two problems separately.
Outcome: The proposed model achieves much higher success rates and crafts more high-quality adversarial examples as compared to baseline methods.
Beyond Quantity: Trajectory Diversity Scaling for Code Agents (2026.findings-acl)

Copied to clipboard

Challenge: Code large language models (LLMs) are becoming tool-interactive agents . quantity-centric scaling exhibits an early bottleneck that underutilizes trajectory data . et al.: a new approach to scale trajectory diversity improves tool-use generalization .
Approach: They propose a Trajectory Diversity Scaling-based data synthesis framework for code agents that scales performance through diversity rather than raw volume.
Outcome: Experiments on general tool-use benchmarks and code agent tasks show that TDScaling improves tool-user generalization and inherent coding proficiency.
Agent-GWO: Collaborative Agents for Dynamic Prompt Optimization in Large Language Models (2026.findings-acl)

Copied to clipboard

Challenge: Existing automatic prompt optimization methods fail to optimize prompts and decoding hyperparameters within a unified framework to achieve stable global improvements.
Approach: They propose a dynamic prompt optimization framework for complex reasoning that unifies prompt templates and decodes hyperparameters as inheritable agent configurations.
Outcome: Experiments on multiple mathematical and hybrid reasoning benchmarks show that Agent-GWO improves accuracy and stability over existing prompt optimization methods.
Interpret and Improve In-Context Learning via the Lens of Input-Label Mappings (2025.acl-long)

Copied to clipboard

Challenge: Large language models excel at downstream NLP tasks through in-context learning . however, the internal mechanisms behind ICL remain under-explored .
Approach: They propose a PC patching approach to identify modules where input-label mappings function . they observe and verify that key heads utilize input-labeled mappings to generate target labels for new queries.
Outcome: The proposed approach detects modules where input-label mappings function . it also detects that key heads use the mappings to generate labels for new queries .
PEMT: Multi-Task Correlation Guided Mixture-of-Experts Enables Parameter-Efficient Transfer Learning (2024.findings-acl)

Copied to clipboard

Challenge: Parameter-efficient fine-tuning (PEFT) is an effective method for adapting pre-trained language models to various tasks efficiently.
Approach: They propose a parameter-efficient fine-tuning framework that captures transferable knowledge as a weighted combination of adapters trained on source tasks.
Outcome: The proposed method yields stable improvements over full fine-tuning and knowledge transferring methods on a broad range of tasks over 17 datasets.
Modeling Semantic Compositionality with Sememe Knowledge (P19-1)

Copied to clipboard

Challenge: Semantic compositionality (SC) is defined as the phenomenon that the meaning of a complex linguistic unit can be composed of the meanings of its constituents.
Approach: They propose to incorporate sememes into SC models and employ them in learning multiword expressions.
Outcome: The proposed models achieve significant performance boost compared to baseline methods without sememe knowledge.

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