PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
April 14, 202416 citationsOpen Access

Exploring the Effectiveness of LLM based Test-driven Interactive Code Generation: User Study and Empirical Evaluation

View Full Paper
SFSarah FakhouryANAaditya NaikGSGeorgios K. Sakkas

Key Points

Key points are not available for this paper at this time.

Abstract

We introduce a novel workflow, TiCoder, designed to enhance the trust and accuracy of LLM-based code generation through interactive and guided intent formalization. TiCoder partially formalizes ambiguous intent in natural language prompts by generating a set of tests to distinguish common divergent behaviours in generated code suggestions. We evaluate the code generation accuracy improvements provided by TiCoder at scale across four competitive LLMs, and evaluate the cost-benefit trade off of evaluating tests surfaced by TiCoder through a user study with 15 participants.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Fakhoury et al. (2024) studied this question.

synapsesocial.com/papers/68e6f3b7b6db64358766eb30https://doi.org/10.1145/3639478.3643525
Ask AI
Helpful
Bookmark
Share
View Full Paper

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Evaluating Large Language Models Trained on Code2021 · 1,463 citations
  2. 2A theory of formal synthesis via inductive learning2017 · 100 citations
  3. 3Knowledge Engineering Using Large Language Models2023 · 272 citations
  4. 4Iterative learning from positive data and negative counterexamples2007 · 11 citations
  5. 5A theory of the learnable1984 · 3,288 citations