{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HJHNNXQ6YYUXINSAAW2JCRQFDC","short_pith_number":"pith:HJHNNXQ6","schema_version":"1.0","canonical_sha256":"3a4ed6de1ec62974364005b491460518bdebfad67462d969bee9aa8ee208a4ac","source":{"kind":"arxiv","id":"2402.18025","version":2},"attestation_state":"computed","paper":{"title":"Hire a Linguist!: Learning Endangered Languages with In-Context Linguistic Descriptions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kexun Zhang, Lei Li, Taiqi He, William Yang Wang, Yee Man Choi, Zhenqiao Song","submitted_at":"2024-02-28T03:44:01Z","abstract_excerpt":"How can large language models (LLMs) process and translate endangered languages? Many languages lack a large corpus to train a decent LLM; therefore existing LLMs rarely perform well in unseen, endangered languages. On the contrary, we observe that 2000 endangered languages, though without a large corpus, have a grammar book or a dictionary. We propose LINGOLLM, a training-free approach to enable an LLM to process unseen languages that hardly occur in its pre-training. Our key insight is to demonstrate linguistic knowledge of an unseen language in an LLM's prompt, including a dictionary, a gra"},"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":"2402.18025","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-28T03:44:01Z","cross_cats_sorted":[],"title_canon_sha256":"c13372a21c489c2fa0fa2102d1352707121174ee781e8b8cf9c8e73bdd6bddd6","abstract_canon_sha256":"18f46d51e0ac86feaf86719c2efd8c450633893e1d9161201205d5b8677a8e14"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:33:59.792775Z","signature_b64":"UG0wXO0PmyWu7WVhZqTa6VH0C0etI+Z7Nl4LLUn5ypyD3UUHAqC8X+hv2v8ZmKkPjUVOtYVCSXhP/Kaa8KdmAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3a4ed6de1ec62974364005b491460518bdebfad67462d969bee9aa8ee208a4ac","last_reissued_at":"2026-07-05T09:33:59.792272Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:33:59.792272Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hire a Linguist!: Learning Endangered Languages with In-Context Linguistic Descriptions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kexun Zhang, Lei Li, Taiqi He, William Yang Wang, Yee Man Choi, Zhenqiao Song","submitted_at":"2024-02-28T03:44:01Z","abstract_excerpt":"How can large language models (LLMs) process and translate endangered languages? Many languages lack a large corpus to train a decent LLM; therefore existing LLMs rarely perform well in unseen, endangered languages. On the contrary, we observe that 2000 endangered languages, though without a large corpus, have a grammar book or a dictionary. We propose LINGOLLM, a training-free approach to enable an LLM to process unseen languages that hardly occur in its pre-training. Our key insight is to demonstrate linguistic knowledge of an unseen language in an LLM's prompt, including a dictionary, a gra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.18025","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/2402.18025/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":"2402.18025","created_at":"2026-07-05T09:33:59.792345+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.18025v2","created_at":"2026-07-05T09:33:59.792345+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.18025","created_at":"2026-07-05T09:33:59.792345+00:00"},{"alias_kind":"pith_short_12","alias_value":"HJHNNXQ6YYUX","created_at":"2026-07-05T09:33:59.792345+00:00"},{"alias_kind":"pith_short_16","alias_value":"HJHNNXQ6YYUXINSA","created_at":"2026-07-05T09:33:59.792345+00:00"},{"alias_kind":"pith_short_8","alias_value":"HJHNNXQ6","created_at":"2026-07-05T09:33:59.792345+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.10066","citing_title":"Dark LLMs: The Growing Threat of Unaligned AI Models","ref_index":4,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HJHNNXQ6YYUXINSAAW2JCRQFDC","json":"https://pith.science/pith/HJHNNXQ6YYUXINSAAW2JCRQFDC.json","graph_json":"https://pith.science/api/pith-number/HJHNNXQ6YYUXINSAAW2JCRQFDC/graph.json","events_json":"https://pith.science/api/pith-number/HJHNNXQ6YYUXINSAAW2JCRQFDC/events.json","paper":"https://pith.science/paper/HJHNNXQ6"},"agent_actions":{"view_html":"https://pith.science/pith/HJHNNXQ6YYUXINSAAW2JCRQFDC","download_json":"https://pith.science/pith/HJHNNXQ6YYUXINSAAW2JCRQFDC.json","view_paper":"https://pith.science/paper/HJHNNXQ6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.18025&json=true","fetch_graph":"https://pith.science/api/pith-number/HJHNNXQ6YYUXINSAAW2JCRQFDC/graph.json","fetch_events":"https://pith.science/api/pith-number/HJHNNXQ6YYUXINSAAW2JCRQFDC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HJHNNXQ6YYUXINSAAW2JCRQFDC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HJHNNXQ6YYUXINSAAW2JCRQFDC/action/storage_attestation","attest_author":"https://pith.science/pith/HJHNNXQ6YYUXINSAAW2JCRQFDC/action/author_attestation","sign_citation":"https://pith.science/pith/HJHNNXQ6YYUXINSAAW2JCRQFDC/action/citation_signature","submit_replication":"https://pith.science/pith/HJHNNXQ6YYUXINSAAW2JCRQFDC/action/replication_record"}},"created_at":"2026-07-05T09:33:59.792345+00:00","updated_at":"2026-07-05T09:33:59.792345+00:00"}