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.
hub
How is chatgpt’s behav- ior changing over time?
11 Pith papers cite this work. Polarity classification is still indexing.
11
Pith papers citing it
hub tools
citation-role summary
dataset 2
background 1
citation-polarity summary
representative citing papers
This systematic survey organizes prompt engineering into a taxonomy of 58 LLM techniques and 40 others, supplies a shared vocabulary, and offers guidelines for state-of-the-art models.
FP16 KV caching in transformers causes deterministic token divergence versus cache-free inference due to non-associative floating-point accumulation orderings.
AgentSPEX is a new language and harness for explicitly specifying and running structured LLM-agent workflows with typed steps, control flow, parallel execution, and a visual editor.
LLM chat systems show large differences in reference quantity and quality, but users rarely click or engage with them.
Self-RAG trains LLMs to adaptively retrieve passages on demand and self-critique using reflection tokens, outperforming ChatGPT and retrieval-augmented Llama2 on QA, reasoning, and fact verification.
GPTFuzz is a black-box fuzzing framework that mutates seed jailbreak templates to automatically generate effective attacks, achieving over 90% success rates on models including ChatGPT and Llama-2.
Four deployment choices—model version, open/closed weight status, provider, and system prompt—each alter LLM-agent intervention rates on forum posts, with closed-weight models declining more on visible challenges than open-weight models.
Execution lineage models AI-native work as a DAG of computations with explicit dependencies, achieving perfect state preservation in controlled update tasks where loop-based agents introduce churn and contamination.
A metadata framework modernizes legacy SAS clinical reporting for AI by adding a non-destructive wrapper layer, achieving 92% code reduction on consolidation and high report parity in validations.
citing papers explorer
-
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.