{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:AXMXD723OGPMR5URJ7O6F2IRNW","short_pith_number":"pith:AXMXD723","schema_version":"1.0","canonical_sha256":"05d971ff5b719ec8f6914fdde2e9116d81877448da9f56e1b464b5375958445b","source":{"kind":"arxiv","id":"2309.10687","version":3},"attestation_state":"computed","paper":{"title":"EchoPrompt: Instructing the Model to Rephrase Queries for Improved In-context Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Rajasekhar Reddy Mekala, Sameer Singh, Yasaman Razeghi","submitted_at":"2023-09-16T00:55:08Z","abstract_excerpt":"Language models are achieving impressive performance on various tasks by aggressively adopting inference-time prompting techniques, such as zero-shot and few-shot prompting. In this work, we introduce EchoPrompt, a simple yet effective approach that prompts the model to rephrase its queries before answering them. EchoPrompt is adapted for both zero-shot and few-shot in-context learning with standard and chain-of-thought prompting. Experimental results show that EchoPrompt yields substantial improvements across all these settings for four families of causal language models. These improvements a"},"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":"2309.10687","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-09-16T00:55:08Z","cross_cats_sorted":[],"title_canon_sha256":"664a4757c1edd48b88bb56a4d735f5d31b1c523ba64a37d81868effdb2d66dbf","abstract_canon_sha256":"4aa85db7b1c4fa83c58af549002cf16b15de83024414dccff01d9336323642f9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:47:26.370906Z","signature_b64":"LMTYaOOjvTduunQVHrk7CTb0x6wTUdXlexeBMuSjE2HSMcjtZBKe9vnt6g8GyuUjv21nSFr56B3dvntXuxucCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"05d971ff5b719ec8f6914fdde2e9116d81877448da9f56e1b464b5375958445b","last_reissued_at":"2026-07-05T07:47:26.370424Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:47:26.370424Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EchoPrompt: Instructing the Model to Rephrase Queries for Improved In-context Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Rajasekhar Reddy Mekala, Sameer Singh, Yasaman Razeghi","submitted_at":"2023-09-16T00:55:08Z","abstract_excerpt":"Language models are achieving impressive performance on various tasks by aggressively adopting inference-time prompting techniques, such as zero-shot and few-shot prompting. In this work, we introduce EchoPrompt, a simple yet effective approach that prompts the model to rephrase its queries before answering them. EchoPrompt is adapted for both zero-shot and few-shot in-context learning with standard and chain-of-thought prompting. Experimental results show that EchoPrompt yields substantial improvements across all these settings for four families of causal language models. These improvements a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.10687","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/2309.10687/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":"2309.10687","created_at":"2026-07-05T07:47:26.370485+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.10687v3","created_at":"2026-07-05T07:47:26.370485+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.10687","created_at":"2026-07-05T07:47:26.370485+00:00"},{"alias_kind":"pith_short_12","alias_value":"AXMXD723OGPM","created_at":"2026-07-05T07:47:26.370485+00:00"},{"alias_kind":"pith_short_16","alias_value":"AXMXD723OGPMR5UR","created_at":"2026-07-05T07:47:26.370485+00:00"},{"alias_kind":"pith_short_8","alias_value":"AXMXD723","created_at":"2026-07-05T07:47:26.370485+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.07972","citing_title":"Zero-shot Video Moment Retrieval via Off-the-shelf Multimodal Large Language Models","ref_index":41,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AXMXD723OGPMR5URJ7O6F2IRNW","json":"https://pith.science/pith/AXMXD723OGPMR5URJ7O6F2IRNW.json","graph_json":"https://pith.science/api/pith-number/AXMXD723OGPMR5URJ7O6F2IRNW/graph.json","events_json":"https://pith.science/api/pith-number/AXMXD723OGPMR5URJ7O6F2IRNW/events.json","paper":"https://pith.science/paper/AXMXD723"},"agent_actions":{"view_html":"https://pith.science/pith/AXMXD723OGPMR5URJ7O6F2IRNW","download_json":"https://pith.science/pith/AXMXD723OGPMR5URJ7O6F2IRNW.json","view_paper":"https://pith.science/paper/AXMXD723","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.10687&json=true","fetch_graph":"https://pith.science/api/pith-number/AXMXD723OGPMR5URJ7O6F2IRNW/graph.json","fetch_events":"https://pith.science/api/pith-number/AXMXD723OGPMR5URJ7O6F2IRNW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AXMXD723OGPMR5URJ7O6F2IRNW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AXMXD723OGPMR5URJ7O6F2IRNW/action/storage_attestation","attest_author":"https://pith.science/pith/AXMXD723OGPMR5URJ7O6F2IRNW/action/author_attestation","sign_citation":"https://pith.science/pith/AXMXD723OGPMR5URJ7O6F2IRNW/action/citation_signature","submit_replication":"https://pith.science/pith/AXMXD723OGPMR5URJ7O6F2IRNW/action/replication_record"}},"created_at":"2026-07-05T07:47:26.370485+00:00","updated_at":"2026-07-05T07:47:26.370485+00:00"}