{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WBR4YGKPETJU323SYBPM2ABLFD","short_pith_number":"pith:WBR4YGKP","schema_version":"1.0","canonical_sha256":"b063cc194f24d34deb72c05ecd002b28d21b09fb25ecc0ef0cf7fd0b5d25a0d3","source":{"kind":"arxiv","id":"2412.07923","version":3},"attestation_state":"computed","paper":{"title":"Asking Again and Again: Exploring LLM Robustness to Repeated Questions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Katharina von der Wense, Mario Sanz-Guerrero, Sagi Shaier","submitted_at":"2024-12-10T21:09:12Z","abstract_excerpt":"This study investigates whether repeating questions within prompts influences the performance of large language models (LLMs). We hypothesize that reiterating a question within a single prompt might enhance the model's focus on key elements of the query. We evaluate five recent LLMs -- including GPT-4o-mini, DeepSeek-V3, and smaller open-source models -- on three reading comprehension datasets under different prompt settings, varying question repetition levels (1, 3, or 5 times per prompt). Our results demonstrate that question repetition can increase models' accuracy by up to $6\\%$. However, "},"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":"2412.07923","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-10T21:09:12Z","cross_cats_sorted":[],"title_canon_sha256":"96b0f999d0821d921f673d3e1e375dfd11d9cf8a767a20158646166fced228b9","abstract_canon_sha256":"448366d8fa3cce709ce7318cd327552f8a5e9f52315bbfa38dead9ecfca99f06"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:29:28.240855Z","signature_b64":"W+FlDNB7XNo1OtUpwix75onbqw7Y27BPkla3ZJkhRl4ItaN0ZaZSN9gVNZZgfaHzo9CECS9YWV+WbH/FY1elDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b063cc194f24d34deb72c05ecd002b28d21b09fb25ecc0ef0cf7fd0b5d25a0d3","last_reissued_at":"2026-07-05T10:29:28.240132Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:29:28.240132Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Asking Again and Again: Exploring LLM Robustness to Repeated Questions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Katharina von der Wense, Mario Sanz-Guerrero, Sagi Shaier","submitted_at":"2024-12-10T21:09:12Z","abstract_excerpt":"This study investigates whether repeating questions within prompts influences the performance of large language models (LLMs). We hypothesize that reiterating a question within a single prompt might enhance the model's focus on key elements of the query. We evaluate five recent LLMs -- including GPT-4o-mini, DeepSeek-V3, and smaller open-source models -- on three reading comprehension datasets under different prompt settings, varying question repetition levels (1, 3, or 5 times per prompt). Our results demonstrate that question repetition can increase models' accuracy by up to $6\\%$. However, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.07923","kind":"arxiv","version":3},"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/2412.07923/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":"2412.07923","created_at":"2026-07-05T10:29:28.240199+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.07923v3","created_at":"2026-07-05T10:29:28.240199+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.07923","created_at":"2026-07-05T10:29:28.240199+00:00"},{"alias_kind":"pith_short_12","alias_value":"WBR4YGKPETJU","created_at":"2026-07-05T10:29:28.240199+00:00"},{"alias_kind":"pith_short_16","alias_value":"WBR4YGKPETJU323S","created_at":"2026-07-05T10:29:28.240199+00:00"},{"alias_kind":"pith_short_8","alias_value":"WBR4YGKP","created_at":"2026-07-05T10:29:28.240199+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.03437","citing_title":"Large Language Models Are Overconfident in Their Own Responses","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WBR4YGKPETJU323SYBPM2ABLFD","json":"https://pith.science/pith/WBR4YGKPETJU323SYBPM2ABLFD.json","graph_json":"https://pith.science/api/pith-number/WBR4YGKPETJU323SYBPM2ABLFD/graph.json","events_json":"https://pith.science/api/pith-number/WBR4YGKPETJU323SYBPM2ABLFD/events.json","paper":"https://pith.science/paper/WBR4YGKP"},"agent_actions":{"view_html":"https://pith.science/pith/WBR4YGKPETJU323SYBPM2ABLFD","download_json":"https://pith.science/pith/WBR4YGKPETJU323SYBPM2ABLFD.json","view_paper":"https://pith.science/paper/WBR4YGKP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.07923&json=true","fetch_graph":"https://pith.science/api/pith-number/WBR4YGKPETJU323SYBPM2ABLFD/graph.json","fetch_events":"https://pith.science/api/pith-number/WBR4YGKPETJU323SYBPM2ABLFD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WBR4YGKPETJU323SYBPM2ABLFD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WBR4YGKPETJU323SYBPM2ABLFD/action/storage_attestation","attest_author":"https://pith.science/pith/WBR4YGKPETJU323SYBPM2ABLFD/action/author_attestation","sign_citation":"https://pith.science/pith/WBR4YGKPETJU323SYBPM2ABLFD/action/citation_signature","submit_replication":"https://pith.science/pith/WBR4YGKPETJU323SYBPM2ABLFD/action/replication_record"}},"created_at":"2026-07-05T10:29:28.240199+00:00","updated_at":"2026-07-05T10:29:28.240199+00:00"}