{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5DXUIFRKFBKFL672AMWUC4TD3U","short_pith_number":"pith:5DXUIFRK","schema_version":"1.0","canonical_sha256":"e8ef44162a285455fbfa032d417263dd39aeb079ac3c925712214984d488a978","source":{"kind":"arxiv","id":"2405.02778","version":1},"attestation_state":"computed","paper":{"title":"Improve Temporal Awareness of LLMs for Sequential Recommendation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Hongning Wang, Ruiyi Zhang, Tong Sun, Yangfeng Ji, Zhendong Chu, Zichao Wang","submitted_at":"2024-05-05T00:21:26Z","abstract_excerpt":"Large language models (LLMs) have demonstrated impressive zero-shot abilities in solving a wide range of general-purpose tasks. However, it is empirically found that LLMs fall short in recognizing and utilizing temporal information, rendering poor performance in tasks that require an understanding of sequential data, such as sequential recommendation. In this paper, we aim to improve temporal awareness of LLMs by designing a principled prompting framework inspired by human cognitive processes. Specifically, we propose three prompting strategies to exploit temporal information within historical"},"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":"2405.02778","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-05-05T00:21:26Z","cross_cats_sorted":[],"title_canon_sha256":"ed74e47076c7c964f2ddc651033a44b3a7a17af3599d86d48c2d4447084bb9dd","abstract_canon_sha256":"5e7f40fa5b1803fa5d52b63c6c349df6fe44852f0ef31e8df3296faa793375c6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:15:53.637953Z","signature_b64":"wVlRYpYej4ZU3PvzKwBGdcKtzs4S+cyY6dHbUt4EtocQzUmYD708Hm6CTRWTfQWw5wjq/qLNBvgb/8jQcYoMCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e8ef44162a285455fbfa032d417263dd39aeb079ac3c925712214984d488a978","last_reissued_at":"2026-07-05T08:15:53.637450Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:15:53.637450Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improve Temporal Awareness of LLMs for Sequential Recommendation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Hongning Wang, Ruiyi Zhang, Tong Sun, Yangfeng Ji, Zhendong Chu, Zichao Wang","submitted_at":"2024-05-05T00:21:26Z","abstract_excerpt":"Large language models (LLMs) have demonstrated impressive zero-shot abilities in solving a wide range of general-purpose tasks. However, it is empirically found that LLMs fall short in recognizing and utilizing temporal information, rendering poor performance in tasks that require an understanding of sequential data, such as sequential recommendation. In this paper, we aim to improve temporal awareness of LLMs by designing a principled prompting framework inspired by human cognitive processes. Specifically, we propose three prompting strategies to exploit temporal information within historical"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.02778","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/2405.02778/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":"2405.02778","created_at":"2026-07-05T08:15:53.637510+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.02778v1","created_at":"2026-07-05T08:15:53.637510+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.02778","created_at":"2026-07-05T08:15:53.637510+00:00"},{"alias_kind":"pith_short_12","alias_value":"5DXUIFRKFBKF","created_at":"2026-07-05T08:15:53.637510+00:00"},{"alias_kind":"pith_short_16","alias_value":"5DXUIFRKFBKFL672","created_at":"2026-07-05T08:15:53.637510+00:00"},{"alias_kind":"pith_short_8","alias_value":"5DXUIFRK","created_at":"2026-07-05T08:15:53.637510+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.03047","citing_title":"Enhancing Temporal Sensitivity of Large Language Model for Recommendation with Counterfactual Tuning","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5DXUIFRKFBKFL672AMWUC4TD3U","json":"https://pith.science/pith/5DXUIFRKFBKFL672AMWUC4TD3U.json","graph_json":"https://pith.science/api/pith-number/5DXUIFRKFBKFL672AMWUC4TD3U/graph.json","events_json":"https://pith.science/api/pith-number/5DXUIFRKFBKFL672AMWUC4TD3U/events.json","paper":"https://pith.science/paper/5DXUIFRK"},"agent_actions":{"view_html":"https://pith.science/pith/5DXUIFRKFBKFL672AMWUC4TD3U","download_json":"https://pith.science/pith/5DXUIFRKFBKFL672AMWUC4TD3U.json","view_paper":"https://pith.science/paper/5DXUIFRK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.02778&json=true","fetch_graph":"https://pith.science/api/pith-number/5DXUIFRKFBKFL672AMWUC4TD3U/graph.json","fetch_events":"https://pith.science/api/pith-number/5DXUIFRKFBKFL672AMWUC4TD3U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5DXUIFRKFBKFL672AMWUC4TD3U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5DXUIFRKFBKFL672AMWUC4TD3U/action/storage_attestation","attest_author":"https://pith.science/pith/5DXUIFRKFBKFL672AMWUC4TD3U/action/author_attestation","sign_citation":"https://pith.science/pith/5DXUIFRKFBKFL672AMWUC4TD3U/action/citation_signature","submit_replication":"https://pith.science/pith/5DXUIFRKFBKFL672AMWUC4TD3U/action/replication_record"}},"created_at":"2026-07-05T08:15:53.637510+00:00","updated_at":"2026-07-05T08:15:53.637510+00:00"}