REVIEW 23 cited by
Does Prompt Formatting Have Any Impact on LLM Performance?
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Does Prompt Formatting Have Any Impact on LLM Performance?
read the original abstract
In the realm of Large Language Models (LLMs), prompt optimization is crucial for model performance. Although previous research has explored aspects like rephrasing prompt contexts, using various prompting techniques (like in-context learning and chain-of-thought), and ordering few-shot examples, our understanding of LLM sensitivity to prompt templates remains limited. Therefore, this paper examines the impact of different prompt templates on LLM performance. We formatted the same contexts into various human-readable templates, including plain text, Markdown, JSON, and YAML, and evaluated their impact across tasks like natural language reasoning, code generation, and translation using OpenAI's GPT models. Experiments show that GPT-3.5-turbo's performance varies by up to 40\% in a code translation task depending on the prompt template, while larger models like GPT-4 are more robust to these variations. Our analysis highlights the need to reconsider the use of fixed prompt templates, as different formats can significantly affect model performance.
Forward citations
Cited by 23 Pith papers
-
Why Do Multi-Agent LLM Systems Fail?
The authors create the first large-scale dataset and taxonomy of failure modes in multi-agent LLM systems to explain their limited performance gains.
-
Rosetta Memory: Adaptive Memory for Cross-LLM Agents
Rosetta Memory trains two profile-conditioned operators with a minimum-gain sampling curriculum and performance-gap reward to enable memory transfer between LLMs, showing gains on multi-hop QA benchmarks and robustnes...
-
Measuring Evaluation-Context Divergence in Open-Weight LLMs: A Paired-Prompt Protocol with Pilot Evidence of Alignment-Pipeline-Specific Heterogeneity
A new paired-prompt protocol reveals alignment-pipeline-specific heterogeneity in how open-weight LLMs respond to evaluation versus deployment framings.
-
IE as Cache: Information Extraction Enhanced Agentic Reasoning
IE-as-Cache framework repurposes information extraction as a dynamic cognitive cache to improve agentic reasoning accuracy in LLMs on challenging benchmarks.
-
Breaking Validity-Induced Boundaries to Expand Algorithm Search Space: A Two-Stage AST-Based Operator for LLM-Driven Automated Heuristic Evolution
A two-stage AST-based crossover and mutation operator with LLM repair expands the search space in LLM-driven heuristic evolution and improves performance on TSP and online bin packing.
-
Persona Non Grata: LLM Persona-Driven Generations in MCQA are Unstable in Distinct Dimensions
Persona-driven generations by LLMs in MCQA tasks exhibit instability that differs systematically by model family, size, domain, and prompt format.
-
Less is More: Quality-Aware Training Data Selection for Scientific Summarization
A 1.88-million-article biomedical summarization dataset is released and quality-aware selection of training data based on abstract alignment outperforms random sampling on factuality metrics.
-
AI Conversational Interviewing: Scaling Up Semi-Structured and In-depth Interviews
AI Conversational Interviewing enables scalable open-ended interviews that capture diverse mental models on topics like migration policy beyond closed-ended surveys, as shown in a 571-respondent study comparing voice,...
-
Benchmarking and Exploring the Capabilities of LLMs for Attack Investigations
AuditBench is a new benchmark of audit logs from 50+ malicious and benign scenarios that evaluates five LLMs on four security investigation tasks and analyzes their performance and error profiles.
-
Same Patient, Different Words, Different Diagnosis? Evaluating Semantic Stability in Clinical LLMs
Domain specialization does not consistently improve clinical LLM robustness to meaning-preserving prompt variations, as shown by new sensitivity metrics on DiagnosisQA and MedQA.
-
Empirical Bayes Conformal Prediction for Vision and Language Models
Empirical Bayes conformal prediction converts score variability into r-value nonconformity scores that preserve target coverage while reducing inclusion of high-variance false candidates in image classification, CLIP ...
-
Divide-Prompt-Refine: a Training-Free, Structure-Aware Framework for Biomedical Abstract Generation
DPR-BAG generates factually grounded biomedical abstracts from full texts via structured BOMRC decomposition, parallel LLM prompting, and coherence refinement without any model training.
-
Divide-Prompt-Refine: a Training-Free, Structure-Aware Framework for Biomedical Abstract Generation
DPR-BAG generates biomedical abstracts from full texts via BOMRC decomposition, parallel LLM summarization, and refinement, showing higher abstractive novelty than baselines while preserving factual consistency on a 4...
-
LPDS: Evaluating LLM Robustness Through Logic-Preserving Difficulty Scaling
LPDS quantifies difficulty of logic-preserving problem variations and searches for the hardest ones, producing up to 5x larger performance drops than random sampling and better robustness gains from fine-tuning on dif...
-
Pop Quiz Attack: Black-box Membership Inference Attacks Against Large Language Models
PopQuiz Attack infers LLM training data membership by turning examples into quiz questions and measuring answer accuracy, reaching 0.873 average ROC-AUC across six models and outperforming prior methods by 20.6%.
-
EHRAG: Bridging Semantic Gaps in Lightweight GraphRAG via Hybrid Hypergraph Construction and Retrieval
EHRAG constructs structural hyperedges from sentence co-occurrence and semantic hyperedges from entity embedding clusters, then applies hybrid diffusion plus topic-aware PPR to retrieve top-k documents, outperforming ...
-
Visual Compositional Tuning
COMPACT synthesizes compositional visual instruction data to reduce VIT training data by 90% while achieving 100.2% of full performance across eight multimodal benchmarks.
-
GRAIN: Group Aggregation via Min-Norm Objective
GRAIN is a gradient aggregation method using min-norm objectives to ensure non-negative inner products with group gradients, yielding tighter uniform stability bounds than SGD under smoothness assumptions.
-
How Should Agents Read Demonstrations? Hierarchical Structure Beats Flat Action Logs
Hierarchically grouped demonstrations raise pass rates from 76.7% to 90.7% on 43 vague-description tasks while flat logs show smaller non-significant gains.
-
Benchmarking Local Language Models for Social Robots using Edge Devices
Benchmarking 25 LLMs on Raspberry Pi hardware shows Granite4 Tiny Hybrid (7B) balances 2.5 tokens/s, 0.90 tokens/J, and 54.6% MMLU while teaching effectiveness does not require high general knowledge scores.
-
MIRAGE: A Micro-Interaction Relational Architecture for Grounded Exploration in Multi-Figure Artworks
MIRAGE improves VLM analysis of multi-figure art by inserting a verifiable structured representation of micro-interactions between spatial grounding and narrative output.
-
Can LLMs Make (Personalized) Access Control Decisions?
LLMs reflect users' privacy preferences in access control decisions with up to 86% agreement and can promote safer behavior, but personalization trades off higher individual match for potentially less secure results w...
-
Generative AI Technologies, Techniques & Tensions: A Primer
Generative AI systems arise from statistical data processing that produces human-like outputs, creating a mismatch with traditional computer expectations and positioning educational researchers to lead in studying and...
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.