Papers by Yiwen Chen

13 papers
Code Representation Pre-training with Complements from Program Executions (2024.emnlp-industry)

Copied to clipboard

Challenge: Existing languages have syntactic representations of code to improve code intelligence, but they are difficult to learn from code.
Approach: They propose to embed dynamic information of programs revealed by their test cases into feature representations of code as complements.
Outcome: The proposed method yields 6%/19% mAP improvements over its masked language modeling counterparts.
Scansion-based Lyrics Generation (2024.lrec-main)

Copied to clipboard

Challenge: a new method for generating lyrics for Mandarin songs is based on scansion . the number of syllables required is variable due to the number and number of notes .
Approach: They propose a method to generate Mandarin lyrics with a good match between melody and tonal contour.
Outcome: The proposed system outperforms all other systems in lyric-melody fit and uses proxies for quantifying creativity.
Rethinking the Role of Entropy in Optimizing Tool-Use Behaviors for Large Language Model Agents (2026.acl-long)

Copied to clipboard

Challenge: Large language models excel in mathematical reasoning and multi-hop question answering tasks, but in long trajectories, agents often invoke tools excessively or inappropriately, increasing computation cost and derailing the reasoning process.
Approach: They propose to use entropy reduction as a supervisory signal to reduce tool calls . they propose to design two reward strategies to address the needs of optimizing tool-use behavior.
Outcome: The proposed reward strategies reduce tool calls by 72.07% and improve performance by 22.27%.
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.
In Prospect and Retrospect: Reflective Memory Management for Long-term Personalized Dialogue Agents (2025.acl-long)

Copied to clipboard

Challenge: Existing approaches to long-term dialogue memory management fail to capture the natural semantic structure of conversations, leading to fragmented and incomplete representations.
Approach: They propose a mechanism that integrates forward- and backward-looking reflections into a personalized memory bank for effective future retrieval.
Outcome: The proposed mechanism outperforms state-of-the-art benchmarks on a long-term dialogue memory model.
YuLan-Mini: Pushing the Limits of Open Data-efficient Language Model (2025.acl-long)

Copied to clipboard

Challenge: prevailing pre-training approaches for large language models involve several complexities.
Approach: They propose a low-cost training recipe and a robust optimization approach to mitigate training instability . they also propose synthesis, curriculum, and data selection pipelines to integrate data .
Outcome: The proposed model achieves top-tier performance among models with similar parameter scale . it is comparable to industry-leading models that require significantly more data .
Understanding Programs by Exploiting (Fuzzing) Test Cases (2023.findings-acl)

Copied to clipboard

Challenge: Semantic understanding of programs has attracted great attention in the community . large language models (LLMs) are capable of learning contextual information from data at scale .
Approach: They propose to incorporate a relationship between inputs and possible outputs into learning for achieving a deeper semantic understanding of programs.
Outcome: The proposed method outperforms current state-of-the-art on two programming tasks and outperformed current state of the art by large margins.
Synthetic Textual Features for the Large-Scale Detection of Basic-level Categories in English and Mandarin (2021.emnlp-main)

Copied to clipboard

Challenge: Basic-level categories are an important psycholinguistic concept introduced by Rosch et al. . an at-scale algorithm for the automatic determination of BLC exists, but it operates without Rosch-style semantic features.
Approach: They propose a method for the detection of BLC at scale that makes use of Rosch-style semantic features.
Outcome: The proposed method outperforms the current SoA in detecting basic-level categories with an accuracy of 75.0% in English and 80.7% in Mandarin.
TextBox 2.0: A Text Generation Library with Pre-trained Language Models (2022.emnlp-demos)

Copied to clipboard

Challenge: TextBox 2.0 focuses on the use of pre-trained language models (PLMs) to generate text.
Approach: They propose a library that integrates pre-trained language models into 13 common text generation tasks and 83 datasets.
Outcome: The proposed library covers 13 common text generation tasks and their corresponding datasets and incorporates 45 PLMs covering general, translation, Chinese, dialogue, controllable, distilled, prompting, and lightweight PLM.
LLMBox: A Comprehensive Library for Large Language Models (2024.acl-demos)

Copied to clipboard

Challenge: a library to facilitate the development, use, and evaluation of large language models (LLMs) is presented.
Approach: They propose a unified library to facilitate the development, use and evaluation of large language models (LLMs).
Outcome: The proposed library is based on extensive experiments in a variety of evaluation settings.
The Program Testing Ability of Large Language Models for Code (2024.emnlp-industry)

Copied to clipboard

Challenge: Recent development of large language models (LLMs) for code shows promise in achieving code intelligence.
Approach: They explore the ability of large language models to generate automated test cases . they show +11.77% and +4.22% higher code pass rates on HumanEval+ .
Outcome: The proposed models show higher pass rates on humanEval+ compared with the current state-of-the-art models.
FreeAL: Towards Human-Free Active Learning in the Era of Large Language Models (2023.emnlp-main)

Copied to clipboard

Challenge: Modern machine learning models require a huge collection of precisely labeled data, which can be labor-intensive and time-consuming.
Approach: They propose a collaborative learning framework that interactively distills and filters the task-specific knowledge from LLMs.
Outcome: The proposed framework improves zero-shot performance on eight benchmark datasets without human supervision.
Behavioral Consistency Validation for LLM Agents: An Analysis of Trading-Style Switching through Stock-Market Simulation (2026.findings-acl)

Copied to clipboard

Challenge: Recent studies have applied Large Language Models (LLMs) as agents in financial stock market simulations to test if micro-level behaviors aggregate into macro-level phenomena.
Approach: They propose four alignment metrics and use Mann–Whitney U tests to compare agents’ style-switching behavior with financial theory.
Outcome: The proposed model is only partially consistent with financial theory.

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