{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4H54EWAQVVAFVGRQCLMZOSDBZR","short_pith_number":"pith:4H54EWAQ","schema_version":"1.0","canonical_sha256":"e1fbc25810ad405a9a3012d9974861cc59700d82fdfd7f3b03ff7d5dfc9b24f0","source":{"kind":"arxiv","id":"2411.10541","version":1},"attestation_state":"computed","paper":{"title":"Does Prompt Formatting Have Any Impact on LLM Performance?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Arshdeep Sekhon, David Koleczek, Franklin X Wang, Jia He, Mukund Rungta, Sadid Hasan","submitted_at":"2024-11-15T19:26:38Z","abstract_excerpt":"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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2411.10541","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-15T19:26:38Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"84aea76843ab1fa7120d9be6d304de547d105898cf55a8a534bd4f11cd4ee58e","abstract_canon_sha256":"cad90ecadcc1d848279ae2ab6629cb13d5ef92d25b6803cfa1525800c15598a4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:36:18.347798Z","signature_b64":"DVW1GUPCQmZdnvQl7jrAnFEnYP2LHBfURx5dFQEzWer0sN5H8NgxmFqAB4KB9OGHR+EgZaoy9L3LZL2J72FXBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e1fbc25810ad405a9a3012d9974861cc59700d82fdfd7f3b03ff7d5dfc9b24f0","last_reissued_at":"2026-07-05T09:36:18.347327Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:36:18.347327Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Does Prompt Formatting Have Any Impact on LLM Performance?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Arshdeep Sekhon, David Koleczek, Franklin X Wang, Jia He, Mukund Rungta, Sadid Hasan","submitted_at":"2024-11-15T19:26:38Z","abstract_excerpt":"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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.10541","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2411.10541/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2411.10541","created_at":"2026-07-05T09:36:18.347386+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.10541v1","created_at":"2026-07-05T09:36:18.347386+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.10541","created_at":"2026-07-05T09:36:18.347386+00:00"},{"alias_kind":"pith_short_12","alias_value":"4H54EWAQVVAF","created_at":"2026-07-05T09:36:18.347386+00:00"},{"alias_kind":"pith_short_16","alias_value":"4H54EWAQVVAFVGRQ","created_at":"2026-07-05T09:36:18.347386+00:00"},{"alias_kind":"pith_short_8","alias_value":"4H54EWAQ","created_at":"2026-07-05T09:36:18.347386+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":23,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24828","citing_title":"Less is More: Quality-Aware Training Data Selection for Scientific Summarization","ref_index":78,"is_internal_anchor":false},{"citing_arxiv_id":"2606.22917","citing_title":"GRAIN: Group Aggregation via Min-Norm Objective","ref_index":82,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20978","citing_title":"How Should Agents Read Demonstrations? Hierarchical Structure Beats Flat Action Logs","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10281","citing_title":"Benchmarking and Exploring the Capabilities of LLMs for Attack Investigations","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07711","citing_title":"Rosetta Memory: Adaptive Memory for Cross-LLM Agents","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00937","citing_title":"Persona Non Grata: LLM Persona-Driven Generations in MCQA are Unstable in Distinct Dimensions","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20628","citing_title":"Divide-Prompt-Refine: a Training-Free, Structure-Aware Framework for Biomedical Abstract Generation","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30646","citing_title":"Same Patient, Different Words, Different Diagnosis? Evaluating Semantic Stability in Clinical LLMs","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20064","citing_title":"AI Conversational Interviewing: Scaling Up Semi-Structured and In-depth Interviews","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23189","citing_title":"Empirical Bayes Conformal Prediction for Vision and Language Models","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2504.21850","citing_title":"Visual Compositional Tuning","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20628","citing_title":"Divide-Prompt-Refine: a Training-Free, Structure-Aware Framework for Biomedical Abstract Generation","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15393","citing_title":"LPDS: Evaluating LLM Robustness Through Logic-Preserving Difficulty Scaling","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2511.20284","citing_title":"Can LLMs Make (Personalized) Access Control Decisions?","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16420","citing_title":"Breaking Validity-Induced Boundaries to Expand Algorithm Search Space: A Two-Stage AST-Based Operator for LLM-Driven Automated Heuristic Evolution","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03111","citing_title":"Benchmarking Local Language Models for Social Robots using Edge Devices","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2503.13657","citing_title":"Why Do Multi-Agent LLM Systems Fail?","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06423","citing_title":"Pop Quiz Attack: Black-box Membership Inference Attacks Against Large Language Models","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14930","citing_title":"IE as Cache: Information Extraction Enhanced Agentic Reasoning","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17458","citing_title":"EHRAG: Bridging Semantic Gaps in Lightweight GraphRAG via Hybrid Hypergraph Construction and Retrieval","ref_index":138,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17497","citing_title":"Generative AI Technologies, Techniques & Tensions: A Primer","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23788","citing_title":"MIRAGE: A Micro-Interaction Relational Architecture for Grounded Exploration in Multi-Figure Artworks","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06327","citing_title":"Measuring Evaluation-Context Divergence in Open-Weight LLMs: A Paired-Prompt Protocol with Pilot Evidence of Alignment-Pipeline-Specific Heterogeneity","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4H54EWAQVVAFVGRQCLMZOSDBZR","json":"https://pith.science/pith/4H54EWAQVVAFVGRQCLMZOSDBZR.json","graph_json":"https://pith.science/api/pith-number/4H54EWAQVVAFVGRQCLMZOSDBZR/graph.json","events_json":"https://pith.science/api/pith-number/4H54EWAQVVAFVGRQCLMZOSDBZR/events.json","paper":"https://pith.science/paper/4H54EWAQ"},"agent_actions":{"view_html":"https://pith.science/pith/4H54EWAQVVAFVGRQCLMZOSDBZR","download_json":"https://pith.science/pith/4H54EWAQVVAFVGRQCLMZOSDBZR.json","view_paper":"https://pith.science/paper/4H54EWAQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.10541&json=true","fetch_graph":"https://pith.science/api/pith-number/4H54EWAQVVAFVGRQCLMZOSDBZR/graph.json","fetch_events":"https://pith.science/api/pith-number/4H54EWAQVVAFVGRQCLMZOSDBZR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4H54EWAQVVAFVGRQCLMZOSDBZR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4H54EWAQVVAFVGRQCLMZOSDBZR/action/storage_attestation","attest_author":"https://pith.science/pith/4H54EWAQVVAFVGRQCLMZOSDBZR/action/author_attestation","sign_citation":"https://pith.science/pith/4H54EWAQVVAFVGRQCLMZOSDBZR/action/citation_signature","submit_replication":"https://pith.science/pith/4H54EWAQVVAFVGRQCLMZOSDBZR/action/replication_record"}},"created_at":"2026-07-05T09:36:18.347386+00:00","updated_at":"2026-07-05T09:36:18.347386+00:00"}