Papers by Ensheng Shi

5 papers
From Conversation to Evaluation: Benchmarking LLMs on Development Knowledge via SimpleDevQA (2026.findings-acl)

Copied to clipboard

Challenge: Existing Dev Knowledge QA benchmarks are limited in development knowledge scope and often not built from real user queries.
Approach: They conduct preliminary analysis of real user–LLM dialogues from WildChat to investigate the importance of Dev Knowledge QA in AI-assisted software development scenarios.
Outcome: The proposed benchmark is based on real user–LLM dialogues from WildChat.
RACE: Retrieval-augmented Commit Message Generation (2022.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to automatically generate commit messages are repetitive or redundant.
Approach: They propose a retrieval-augmented neural commit message generation method which treats the retrieved similar commit as an exemplar and leverages it to generate an accurate commit message.
Outcome: The proposed method outperforms baselines on a large dataset with five programming languages and can boost existing Seq2Seq models in commit message generation.
CAST: Enhancing Code Summarization with Hierarchical Splitting and Reconstruction of Abstract Syntax Trees (2021.emnlp-main)

Copied to clipboard

Challenge: Existing methods for code summarization do not capture rich information in ASTs . existing methods are labor-intensive and time-consuming to document code with good summaries manually.
Approach: They propose a model that hierarchically splits and reconstructs ASTs by a neural network . they propose to use AST embeddings and a vanilla code token encoder to generate the model .
Outcome: The proposed model splits and reconstructs ASTs into subtrees and then aggregates embeddings of subtreas to get the complete AST.
UCoder: Unsupervised Code Generation by Internal Probing of Large Language Models (2026.findings-acl)

Copied to clipboard

Challenge: Large language models (LLMs) have demonstrated remarkable capabilities in code generation tasks, but their effectiveness relies on supervised training with extensive labeled data and computational resources.
Approach: They propose an unsupervised method that leverages Internal Probing of Large language models for Code generation without any external corpus, even unlabeled code snippets.
Outcome: The proposed method can achieve competitive performance compared to supervised approaches while reducing the dependency on labeled data and computational resources.
Speed Up Your Code: Progressive Code Acceleration Through Bidirectional Tree Editing (2025.acl-long)

Copied to clipboard

Challenge: Existing training methods, such as direct instruction fine-tuning, overlook hierarchical relationships among acceleration patterns.
Approach: They propose a new training paradigm that uses bidirectional tree editing and progressive code acceleration learning to improve LLMs’ CA capabilities.
Outcome: The proposed training paradigm outperforms prompt-enhanced GPT-4 and current training-based methods on average across five programming languages.

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