{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:LQC67RXYVAAP3DRB43HHA5RQMA","short_pith_number":"pith:LQC67RXY","schema_version":"1.0","canonical_sha256":"5c05efc6f8a800fd8e21e6ce707630603c6db731351d6197220169c6ef394d7c","source":{"kind":"arxiv","id":"2304.09542","version":3},"attestation_state":"computed","paper":{"title":"Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Dawei Yin, Lingyong Yan, Pengjie Ren, Shuaiqiang Wang, Weiwei Sun, Xinyu Ma, Zhaochun Ren, Zhumin Chen","submitted_at":"2023-04-19T10:16:03Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated remarkable zero-shot generalization across various language-related tasks, including search engines. However, existing work utilizes the generative ability of LLMs for Information Retrieval (IR) rather than direct passage ranking. The discrepancy between the pre-training objectives of LLMs and the ranking objective poses another challenge. In this paper, we first investigate generative LLMs such as ChatGPT and GPT-4 for relevance ranking in IR. Surprisingly, our experiments reveal that properly instructed LLMs can deliver competitive, even superio"},"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":"2304.09542","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-04-19T10:16:03Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"e521e5aba10ad0d46db0381efd9ead64e47434d067f7d59a7f7006c1a415ee62","abstract_canon_sha256":"a9915c51742ec2f0dee2295c67f27c5d06b1ece4052367972c7a28533bf17385"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:54:42.585790Z","signature_b64":"uXn1B9/lwdTaa5oxioeOZMJ/71DoKfEAEijvuY7r/ytMjNC1VXsJ4pbYU0M37kndbUh5CKx/iF+4WXwWgbb+Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5c05efc6f8a800fd8e21e6ce707630603c6db731351d6197220169c6ef394d7c","last_reissued_at":"2026-07-05T09:54:42.585342Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:54:42.585342Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Dawei Yin, Lingyong Yan, Pengjie Ren, Shuaiqiang Wang, Weiwei Sun, Xinyu Ma, Zhaochun Ren, Zhumin Chen","submitted_at":"2023-04-19T10:16:03Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated remarkable zero-shot generalization across various language-related tasks, including search engines. However, existing work utilizes the generative ability of LLMs for Information Retrieval (IR) rather than direct passage ranking. The discrepancy between the pre-training objectives of LLMs and the ranking objective poses another challenge. In this paper, we first investigate generative LLMs such as ChatGPT and GPT-4 for relevance ranking in IR. Surprisingly, our experiments reveal that properly instructed LLMs can deliver competitive, even superio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.09542","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/2304.09542/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":"2304.09542","created_at":"2026-07-05T09:54:42.585397+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.09542v3","created_at":"2026-07-05T09:54:42.585397+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.09542","created_at":"2026-07-05T09:54:42.585397+00:00"},{"alias_kind":"pith_short_12","alias_value":"LQC67RXYVAAP","created_at":"2026-07-05T09:54:42.585397+00:00"},{"alias_kind":"pith_short_16","alias_value":"LQC67RXYVAAP3DRB","created_at":"2026-07-05T09:54:42.585397+00:00"},{"alias_kind":"pith_short_8","alias_value":"LQC67RXY","created_at":"2026-07-05T09:54:42.585397+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":29,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.05968","citing_title":"InfluMatch: Frontier-Quality KOL Search at 4B-Model Cost","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2607.02387","citing_title":"Bringing Agentic Search to Earth Observation Data Discovery","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28369","citing_title":"Multimodal and Multiscale Spatial-Temporal Semantic Search and Recommendation with AI Foundation Models","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04727","citing_title":"EviRank: Evidence-Based Confidence Estimation for LLM-Based Ranking","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03728","citing_title":"Re-Ranking Through an Attribution Lens for Citation Quality in Legal QA","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27429","citing_title":"Ocean4Rec: Offline LLM-Derived OCEAN Profiles for Request-Time VOD Reranking","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28737","citing_title":"5ting at SemEval-2026 Task 8: Strong End-to-End Multi-Turn RAG via LLM-Based Reranking and Faithfulness Control","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28369","citing_title":"Multimodal and Multiscale Spatial-Temporal Semantic Search and Recommendation with AI Foundation Models","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27856","citing_title":"Fine-Tuned LLM as a Complementary Predictor Improving Ads System","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27810","citing_title":"LRanker: LLM Ranker for Massive Candidates","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2409.14634","citing_title":"Human-LLM Compound System for Scientific Ideation through Facet Recombination and Novelty Evaluation","ref_index":71,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22501","citing_title":"BeLink: Biomedical Entity Linking Meets Generative Re-Ranking","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2509.00303","citing_title":"Access Paths for Efficient Ordering with Large Language Models","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18768","citing_title":"ClinQueryAgent: A Conversational Agent for Population Health Management","ref_index":211,"is_internal_anchor":false},{"citing_arxiv_id":"2506.04565","citing_title":"From Standalone LLMs to Integrated Intelligence: A Survey of Compound Al Systems","ref_index":166,"is_internal_anchor":false},{"citing_arxiv_id":"2510.07048","citing_title":"Search-R3: Unifying Reasoning and Embedding in Large Language Models","ref_index":69,"is_internal_anchor":false},{"citing_arxiv_id":"2602.22220","citing_title":"What Makes an Ideal Quote? Recommending \"Unexpected yet Rational\" Quotations via Novelty","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2312.02724","citing_title":"RankZephyr: Effective and Robust Zero-Shot Listwise Reranking is a Breeze!","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2603.15970","citing_title":"100x Cost & Latency Reduction: Performance Analysis of AI Query Approximation using Lightweight Proxy Models","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03724","citing_title":"Rank, Don't Generate: Statement-level Ranking for Explainable Recommendation","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11272","citing_title":"Localization Boosting for Growth Markets: Mitigating Cross-Locale Behavioral Bias in Learning-to-Rank","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27577","citing_title":"Reproducing Adaptive Reranking for Reasoning-Intensive IR","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26483","citing_title":"Efficient Listwise Reranking with Compressed Document Representations","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22180","citing_title":"ResRank: Unifying Retrieval and Listwise Reranking via End-to-End Joint Training with Residual Passage Compression","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19899","citing_title":"A Reproducibility Study of Metacognitive Retrieval-Augmented Generation","ref_index":43,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LQC67RXYVAAP3DRB43HHA5RQMA","json":"https://pith.science/pith/LQC67RXYVAAP3DRB43HHA5RQMA.json","graph_json":"https://pith.science/api/pith-number/LQC67RXYVAAP3DRB43HHA5RQMA/graph.json","events_json":"https://pith.science/api/pith-number/LQC67RXYVAAP3DRB43HHA5RQMA/events.json","paper":"https://pith.science/paper/LQC67RXY"},"agent_actions":{"view_html":"https://pith.science/pith/LQC67RXYVAAP3DRB43HHA5RQMA","download_json":"https://pith.science/pith/LQC67RXYVAAP3DRB43HHA5RQMA.json","view_paper":"https://pith.science/paper/LQC67RXY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.09542&json=true","fetch_graph":"https://pith.science/api/pith-number/LQC67RXYVAAP3DRB43HHA5RQMA/graph.json","fetch_events":"https://pith.science/api/pith-number/LQC67RXYVAAP3DRB43HHA5RQMA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LQC67RXYVAAP3DRB43HHA5RQMA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LQC67RXYVAAP3DRB43HHA5RQMA/action/storage_attestation","attest_author":"https://pith.science/pith/LQC67RXYVAAP3DRB43HHA5RQMA/action/author_attestation","sign_citation":"https://pith.science/pith/LQC67RXYVAAP3DRB43HHA5RQMA/action/citation_signature","submit_replication":"https://pith.science/pith/LQC67RXYVAAP3DRB43HHA5RQMA/action/replication_record"}},"created_at":"2026-07-05T09:54:42.585397+00:00","updated_at":"2026-07-05T09:54:42.585397+00:00"}