{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:5P4X7FCIJEMTVCSS55PZMETI4S","short_pith_number":"pith:5P4X7FCI","schema_version":"1.0","canonical_sha256":"ebf97f944849193a8a52ef5f961268e49daedd9deaaa136f4773969597ea8a28","source":{"kind":"arxiv","id":"2305.11792","version":2},"attestation_state":"computed","paper":{"title":"Cue-CoT: Chain-of-thought Prompting for Responding to In-depth Dialogue Questions with LLMs","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bin Liang, Fei Mi, Hongru Wang, Kam-Fai Wong, Ruifeng Xu, Rui Wang, Yang Deng, Zezhong Wang","submitted_at":"2023-05-19T16:27:43Z","abstract_excerpt":"Large Language Models (LLMs), such as \\texttt{ChatGPT}, greatly empower dialogue systems with strong language understanding and generation capabilities. However, most of the previous works prompt the LLMs to directly generate a response based on the dialogue context, overlooking the underlying linguistic cues about the user status exhibited in the context. Such in-depth dialogue scenarios are challenging for existing LLMs to figure out the user's hidden needs and respond satisfactorily through a single-step inference. To this end, we propose a novel linguistic cue-based chain-of-thoughts (\\tex"},"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":"2305.11792","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-19T16:27:43Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4915cc7c710c6049c9731bc2d3c191f2559c9460db230c936d0f0fa2cc1f820f","abstract_canon_sha256":"ac188c01960df259ac4c9630720aa80313940f06778ea3d4af36591bb528f8f0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:01:01.397830Z","signature_b64":"OMk6JKzxJAnHq5iSTQTq/ekC6JQahAh6nmD2p9ASckI97JEA1D/kvTX+o/Ziu7BQd7rZFAa0rVrVifo4drgQCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ebf97f944849193a8a52ef5f961268e49daedd9deaaa136f4773969597ea8a28","last_reissued_at":"2026-07-05T07:01:01.397379Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:01:01.397379Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cue-CoT: Chain-of-thought Prompting for Responding to In-depth Dialogue Questions with LLMs","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bin Liang, Fei Mi, Hongru Wang, Kam-Fai Wong, Ruifeng Xu, Rui Wang, Yang Deng, Zezhong Wang","submitted_at":"2023-05-19T16:27:43Z","abstract_excerpt":"Large Language Models (LLMs), such as \\texttt{ChatGPT}, greatly empower dialogue systems with strong language understanding and generation capabilities. However, most of the previous works prompt the LLMs to directly generate a response based on the dialogue context, overlooking the underlying linguistic cues about the user status exhibited in the context. Such in-depth dialogue scenarios are challenging for existing LLMs to figure out the user's hidden needs and respond satisfactorily through a single-step inference. To this end, we propose a novel linguistic cue-based chain-of-thoughts (\\tex"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.11792","kind":"arxiv","version":2},"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/2305.11792/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":"2305.11792","created_at":"2026-07-05T07:01:01.397439+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.11792v2","created_at":"2026-07-05T07:01:01.397439+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.11792","created_at":"2026-07-05T07:01:01.397439+00:00"},{"alias_kind":"pith_short_12","alias_value":"5P4X7FCIJEMT","created_at":"2026-07-05T07:01:01.397439+00:00"},{"alias_kind":"pith_short_16","alias_value":"5P4X7FCIJEMTVCSS","created_at":"2026-07-05T07:01:01.397439+00:00"},{"alias_kind":"pith_short_8","alias_value":"5P4X7FCI","created_at":"2026-07-05T07:01:01.397439+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.15588","citing_title":"\"Excuse me, may I say something...\" CoLabScience, A Proactive AI Assistant for Biomedical Discovery and LLM-Expert Collaborations","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5P4X7FCIJEMTVCSS55PZMETI4S","json":"https://pith.science/pith/5P4X7FCIJEMTVCSS55PZMETI4S.json","graph_json":"https://pith.science/api/pith-number/5P4X7FCIJEMTVCSS55PZMETI4S/graph.json","events_json":"https://pith.science/api/pith-number/5P4X7FCIJEMTVCSS55PZMETI4S/events.json","paper":"https://pith.science/paper/5P4X7FCI"},"agent_actions":{"view_html":"https://pith.science/pith/5P4X7FCIJEMTVCSS55PZMETI4S","download_json":"https://pith.science/pith/5P4X7FCIJEMTVCSS55PZMETI4S.json","view_paper":"https://pith.science/paper/5P4X7FCI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.11792&json=true","fetch_graph":"https://pith.science/api/pith-number/5P4X7FCIJEMTVCSS55PZMETI4S/graph.json","fetch_events":"https://pith.science/api/pith-number/5P4X7FCIJEMTVCSS55PZMETI4S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5P4X7FCIJEMTVCSS55PZMETI4S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5P4X7FCIJEMTVCSS55PZMETI4S/action/storage_attestation","attest_author":"https://pith.science/pith/5P4X7FCIJEMTVCSS55PZMETI4S/action/author_attestation","sign_citation":"https://pith.science/pith/5P4X7FCIJEMTVCSS55PZMETI4S/action/citation_signature","submit_replication":"https://pith.science/pith/5P4X7FCIJEMTVCSS55PZMETI4S/action/replication_record"}},"created_at":"2026-07-05T07:01:01.397439+00:00","updated_at":"2026-07-05T07:01:01.397439+00:00"}