Defines documentation-to-code equivalence and introduces Documentary to generate matching docs for 53.4% of function snippets, raising LLM output prediction accuracy by 12.8-24.5% over human-written docs.
arXiv preprint (2025), https://arxiv.org/abs/ 2406.18403
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
citation-role summary
background 4
citation-polarity summary
roles
background 3representative citing papers
An audit of one million Korean synthetic personas shows marginal demographic alignment does not preserve joint distributions, with three specific mismatches identified via a new Independence-Assumption Footprint method.
The paper delivers a taxonomy of seven LLM study types in software engineering along with eight guidelines that separate mandatory requirements from recommended practices to address reproducibility challenges.
Instructions trigger a production-centered mechanism in language models, with task-specific information stable in input tokens but varying strongly in output tokens and correlating with behavior.
Generative AI evaluation must shift from static benchmark scores to measuring sustained improvements in human capabilities within specific deployment contexts.
Large-scale data from an AI platform confirms students have consistent learning rates (IQR 7.01-8.25 opportunities to 80% mastery) despite variable starting knowledge, replicating prior findings with automated knowledge components.
A survey that organizes LLMs-as-judges research into functionality, methodology, applications, meta-evaluation, and limitations.
citing papers explorer
-
Natural Language-Focused Software Engineering via Code-Documentation Equivalence
Defines documentation-to-code equivalence and introduces Documentary to generate matching docs for 53.4% of function snippets, raising LLM output prediction accuracy by 12.8-24.5% over human-written docs.
-
Marginal Alignment Does Not Guarantee Joint-Distribution Fidelity: An Official-Reference Audit of Nemotron-Personas-Korea with Cross-Locale Replication
An audit of one million Korean synthetic personas shows marginal demographic alignment does not preserve joint distributions, with three specific mismatches identified via a new Independence-Assumption Footprint method.
-
Guidelines for Empirical Studies in Software Engineering involving Large Language Models
The paper delivers a taxonomy of seven LLM study types in software engineering along with eight guidelines that separate mandatory requirements from recommended practices to address reproducibility challenges.
-
Instructions Shape Production of Language, not Processing
Instructions trigger a production-centered mechanism in language models, with task-specific information stable in input tokens but varying strongly in output tokens and correlating with behavior.
-
Benchmarked Yet Not Measured -- Generative AI Should be Evaluated Against Real-World Utility
Generative AI evaluation must shift from static benchmark scores to measuring sustained improvements in human capabilities within specific deployment contexts.
-
Personalized AI Practice Replicates Learning Rate Regularity at Scale
Large-scale data from an AI platform confirms students have consistent learning rates (IQR 7.01-8.25 opportunities to 80% mastery) despite variable starting knowledge, replicating prior findings with automated knowledge components.
-
LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods
A survey that organizes LLMs-as-judges research into functionality, methodology, applications, meta-evaluation, and limitations.
- Auditing Automated Evaluation, Error Propagation, and Runtime Mitigation in Tool-Using Language Agents