Papers by Da Song

4 papers
Benchmarking Language Models for Code Syntax Understanding (2022.findings-emnlp)

Copied to clipboard

Challenge: Pre-trained language models capture the syntactic rules of natural languages without fine-tuning on syntax understanding tasks.
Approach: They propose a benchmarking test to compare pre-trained language models with a large-scale dataset of programs annotated with syntactic relationships in their corresponding abstract syntax trees.
Outcome: The proposed model fails to match baselines based on positional offsets and keywords.
TESTEVAL: Benchmarking Large Language Models for Test Case Generation (2025.findings-naacl)

Copied to clipboard

Challenge: Existing methods to generate test cases using large language models are limited in their ability to generate unit test cases.
Approach: They propose a test case generation benchmark that uses large language models to generate unit test cases.
Outcome: The proposed test case generation benchmarks compare LLMs with commercial and open-source LLM platforms and find that they lack the ability to comprehend program logic and execution paths.
To the Globe (TTG): Towards Language-Driven Guaranteed Travel Planning (2024.emnlp-demo)

Copied to clipboard

Challenge: a new system that takes natural language requests from users generates and trains optimal travel plans . a user can provide instructions and an agent provides optimal solutions . the system takes 5seconds to reply to the user request with guaranteed itineraries .
Approach: They propose a real-time demo system that takes natural language requests from users . it translates requests to symbolic form and produces optimal travel itineraries with LLM .
Outcome: The proposed system produces optimal travel itineraries with mixed integer linear programming solvers.
Trial and Error: Exploration-Based Trajectory Optimization of LLM Agents (2024.acl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) have become integral components in various autonomous agent systems.
Approach: They propose an exploration-based trajectory optimization approach that allows agents to learn from their exploration failures.
Outcome: The proposed method outperforms baseline methods on three complex tasks by a large margin.

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