PIAST iteratively optimizes few-shot examples in prompts via Monte Carlo Shapley value estimation, outperforming prior automatic prompting methods and setting new SOTA on classification, simplification, and GSM8K with modest compute.
arXiv preprint arXiv:2310.14735 (2023)
11 Pith papers cite this work, alongside 136 external citations. Polarity classification is still indexing.
11
Pith papers citing it
136
external citations · external index
citation-role summary
background 2
baseline 1
citation-polarity summary
representative citing papers
Meta Agent Search uses a meta-agent to iteratively program novel agentic systems in code, producing agents that outperform state-of-the-art hand-designed ones across coding, science, and math while transferring across domains and models.
The paper characterizes deductive stereotyping in LLMs and introduces Fair-GCG to discover injection phrases that improve fairness across benchmarks, reasoning, and real-world tasks.
MA-CoT prompting reduces security findings in LLM-generated code by 57.6% on a 200-task dataset and 94.5% on LLMSecEval across C, Java, and Python, outperforming vanilla, zero-shot, and standard CoT strategies.
PromptAudit evaluates five prompting strategies across five LLMs on 1000 CVEs and finds chain-of-thought prompting yields the strongest overall performance while adaptive chain-of-thought and self-consistency reduce effective results.
GPT-4o identified only 21.2% of the usability issues found by human experts in heuristic evaluation, while discovering 27 additional issues and exhibiting difficulties with certain heuristics and generating false positives.
IstGPT combines LLMs for graph extraction with improved GNNs for anomaly detection in industrial cyber-physical systems and reports best F1 and eTaF1 scores across nine datasets versus 12 baselines.
LLMs for smart contract security analysis show lexical bias from identifier names causing high false positives, with prompting creating precision-recall trade-offs, positioning them as complements rather than replacements for static analysis tools.
GPT-4o classified student explanations on the Energy and Momentum Conceptual Survey with 0-3% discrepancy from human graders and produced incorrect-explanation categories distinct from multiple-choice distractors.
A systematic survey categorizes prompt engineering methods for LLMs and VLMs by application area, summarizing methodologies, applications, models, datasets, strengths, and limitations for each technique along with a taxonomy and summary table.
The paper reviews the background, technology, applications, limitations, and future directions of OpenAI's Sora text-to-video generative model based on public information.
citing papers explorer
-
PIAST: Rapid Prompting with In-context Augmentation for Scarce Training data
PIAST iteratively optimizes few-shot examples in prompts via Monte Carlo Shapley value estimation, outperforming prior automatic prompting methods and setting new SOTA on classification, simplification, and GSM8K with modest compute.
-
Automated Design of Agentic Systems
Meta Agent Search uses a meta-agent to iteratively program novel agentic systems in code, producing agents that outperform state-of-the-art hand-designed ones across coding, science, and math while transferring across domains and models.
-
Wait, am I Being Fair? Characterizing Deductive Stereotyping and Mitigating It with Fair-GCG
The paper characterizes deductive stereotyping in LLMs and introduces Fair-GCG to discover injection phrases that improve fairness across benchmarks, reasoning, and real-world tasks.
-
Enhancing Reliability in LLM-Based Secure Code Generation
MA-CoT prompting reduces security findings in LLM-generated code by 57.6% on a 200-task dataset and 94.5% on LLMSecEval across C, Java, and Python, outperforming vanilla, zero-shot, and standard CoT strategies.
-
PromptAudit: Auditing Prompt Sensitivity in LLM-Based Vulnerability Detection
PromptAudit evaluates five prompting strategies across five LLMs on 1000 CVEs and finds chain-of-thought prompting yields the strongest overall performance while adaptive chain-of-thought and self-consistency reduce effective results.
-
Can GPT-4o Evaluate Usability Like Human Experts? A Comparative Study on Issue Identification in Heuristic Evaluation
GPT-4o identified only 21.2% of the usability issues found by human experts in heuristic evaluation, while discovering 27 additional issues and exhibiting difficulties with certain heuristics and generating false positives.
-
IstGPT: LLM-based Anomaly Detection for Spatial-Temporal Graph in Industrial Systems
IstGPT combines LLMs for graph extraction with improved GNNs for anomaly detection in industrial cyber-physical systems and reports best F1 and eTaF1 scores across nine datasets versus 12 baselines.
-
Benchmarking LLM-Based Static Analysis for Secure Smart Contract Development: Reliability, Limitations, and Potential Hybrid Solutions
LLMs for smart contract security analysis show lexical bias from identifier names causing high false positives, with prompting creating precision-recall trade-offs, positioning them as complements rather than replacements for static analysis tools.
-
Using an LLM to Investigate Students' Explanations on Conceptual Physics Questions
GPT-4o classified student explanations on the Energy and Momentum Conceptual Survey with 0-3% discrepancy from human graders and produced incorrect-explanation categories distinct from multiple-choice distractors.
-
A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications
A systematic survey categorizes prompt engineering methods for LLMs and VLMs by application area, summarizing methodologies, applications, models, datasets, strengths, and limitations for each technique along with a taxonomy and summary table.
-
Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models
The paper reviews the background, technology, applications, limitations, and future directions of OpenAI's Sora text-to-video generative model based on public information.