{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:CU5U5T6FGP3KJS6S32K6RHFU4H","short_pith_number":"pith:CU5U5T6F","schema_version":"1.0","canonical_sha256":"153b4ecfc533f6a4cbd2de95e89cb4e1c31a5b9f4e6a52e0e44d192416e9e957","source":{"kind":"arxiv","id":"2310.06839","version":2},"attestation_state":"computed","paper":{"title":"LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Chin-Yew Lin, Dongsheng Li, Huiqiang Jiang, Lili Qiu, Qianhui Wu, Xufang Luo, Yuqing Yang","submitted_at":"2023-10-10T17:59:58Z","abstract_excerpt":"In long context scenarios, large language models (LLMs) face three main challenges: higher computational cost, performance reduction, and position bias. Research indicates that LLM performance hinges on the density and position of key information in the input prompt. Inspired by these findings, we propose LongLLMLingua for prompt compression towards improving LLMs' perception of the key information to simultaneously address the three challenges. Our extensive evaluation across various long context scenarios demonstrates that LongLLMLingua not only enhances performance but also significantly re"},"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":"2310.06839","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-10T17:59:58Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"1aa7d57f2fd9fc61064f415cdec9b5145c52e6f0248a39bd02e58e94ea0726f6","abstract_canon_sha256":"87e6bea88a60dd6e466a96fb281a67899535d9a7cee2443505ca6953dcd100f4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:54:04.375936Z","signature_b64":"xw0SfZDACBTRcfmP2lz5r6kuNBoAv3CgSPWErSwbuv3/1SkRFIt+T8Wi9R646x3WVt+Vzdy+duCookDR6CdfDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"153b4ecfc533f6a4cbd2de95e89cb4e1c31a5b9f4e6a52e0e44d192416e9e957","last_reissued_at":"2026-07-05T08:54:04.375482Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:54:04.375482Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Chin-Yew Lin, Dongsheng Li, Huiqiang Jiang, Lili Qiu, Qianhui Wu, Xufang Luo, Yuqing Yang","submitted_at":"2023-10-10T17:59:58Z","abstract_excerpt":"In long context scenarios, large language models (LLMs) face three main challenges: higher computational cost, performance reduction, and position bias. Research indicates that LLM performance hinges on the density and position of key information in the input prompt. Inspired by these findings, we propose LongLLMLingua for prompt compression towards improving LLMs' perception of the key information to simultaneously address the three challenges. Our extensive evaluation across various long context scenarios demonstrates that LongLLMLingua not only enhances performance but also significantly re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.06839","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/2310.06839/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":"2310.06839","created_at":"2026-07-05T08:54:04.375538+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.06839v2","created_at":"2026-07-05T08:54:04.375538+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.06839","created_at":"2026-07-05T08:54:04.375538+00:00"},{"alias_kind":"pith_short_12","alias_value":"CU5U5T6FGP3K","created_at":"2026-07-05T08:54:04.375538+00:00"},{"alias_kind":"pith_short_16","alias_value":"CU5U5T6FGP3KJS6S","created_at":"2026-07-05T08:54:04.375538+00:00"},{"alias_kind":"pith_short_8","alias_value":"CU5U5T6F","created_at":"2026-07-05T08:54:04.375538+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":25,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2607.08032","citing_title":"What to Keep, What to Forget: A Rate--Distortion View of Memory Compaction in LLMs and Agents","ref_index":54,"is_internal_anchor":true},{"citing_arxiv_id":"2607.05378","citing_title":"CompactionRL: Reinforcement Learning with Context Compaction for Long-Horizon Agents","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2606.20295","citing_title":"Token-Operations-Oriented Inference Optimization Techniques for Large Models","ref_index":131,"is_internal_anchor":false},{"citing_arxiv_id":"2607.01241","citing_title":"Mapping Text to Multiplex Graph: Prompt Compression as L\\'evy Walk-Guided Graph Pruning","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08151","citing_title":"Decision-Aware Memory Cards: Counterfactual-Inspired Context Selection and Compression for Tool-Using LLM Agents","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06337","citing_title":"TokenMizer: Graph-Structured Session Memory for Long-Horizon LLM Context Management","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24541","citing_title":"SemanticZip: A Pilot Framework for Lossy Text Compression with LLMs as Semantic Decompressors","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26165","citing_title":"Tool-Schema Compression Enables Agentic RAG Under Constrained Context Budgets","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27494","citing_title":"Grounded Cache Routing for Retrieval-Augmented Generation: When Is It Safe to Reuse an Answer?","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2508.12043","citing_title":"Talk Less, Fly Lighter: Autonomous Semantic Compression for UAV Swarm Communication via LLMs","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2312.10997","citing_title":"Retrieval-Augmented Generation for Large Language Models: A Survey","ref_index":101,"is_internal_anchor":false},{"citing_arxiv_id":"2409.01579","citing_title":"AdaComp: Extractive Context Compression with Adaptive Predictor for Retrieval-Augmented Large Language Models","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2409.06679","citing_title":"E2LLM: Encoder Elongated Large Language Models for Long-Context Understanding and Reasoning","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2502.14644","citing_title":"LIFT: A Novel Framework for Enhancing Long-Context Understanding of LLMs via Long Input Fine-Tuning","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2502.14925","citing_title":"CODEPROMPTZIP: Code-specific Prompt Compression for Retrieval-Augmented Generation in Coding Tasks with LMs","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14156","citing_title":"Compressed-Sensing-Guided, Inference-Aware Structured Reduction for Large Language Models","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2404.14294","citing_title":"A Survey on Efficient Inference for Large Language Models","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2503.05592","citing_title":"R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2501.05366","citing_title":"Search-o1: Agentic Search-Enhanced Large Reasoning Models","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09611","citing_title":"Byte-Exact Deduplication in Retrieval-Augmented Generation: A Three-Regime Empirical Analysis Across Public Benchmarks","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04107","citing_title":"TSCG: Deterministic Tool-Schema Compilation for Agentic LLM Deployments","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12376","citing_title":"Cooperative Memory Paging with Keyword Bookmarks for Long-Horizon LLM Conversations","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2404.06654","citing_title":"RULER: What's the Real Context Size of Your Long-Context Language Models?","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13725","citing_title":"On the Effectiveness of Context Compression for Repository-Level Tasks: An Empirical Investigation","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20727","citing_title":"Supplement Generation Training for Enhancing Agentic Task Performance","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CU5U5T6FGP3KJS6S32K6RHFU4H","json":"https://pith.science/pith/CU5U5T6FGP3KJS6S32K6RHFU4H.json","graph_json":"https://pith.science/api/pith-number/CU5U5T6FGP3KJS6S32K6RHFU4H/graph.json","events_json":"https://pith.science/api/pith-number/CU5U5T6FGP3KJS6S32K6RHFU4H/events.json","paper":"https://pith.science/paper/CU5U5T6F"},"agent_actions":{"view_html":"https://pith.science/pith/CU5U5T6FGP3KJS6S32K6RHFU4H","download_json":"https://pith.science/pith/CU5U5T6FGP3KJS6S32K6RHFU4H.json","view_paper":"https://pith.science/paper/CU5U5T6F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.06839&json=true","fetch_graph":"https://pith.science/api/pith-number/CU5U5T6FGP3KJS6S32K6RHFU4H/graph.json","fetch_events":"https://pith.science/api/pith-number/CU5U5T6FGP3KJS6S32K6RHFU4H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CU5U5T6FGP3KJS6S32K6RHFU4H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CU5U5T6FGP3KJS6S32K6RHFU4H/action/storage_attestation","attest_author":"https://pith.science/pith/CU5U5T6FGP3KJS6S32K6RHFU4H/action/author_attestation","sign_citation":"https://pith.science/pith/CU5U5T6FGP3KJS6S32K6RHFU4H/action/citation_signature","submit_replication":"https://pith.science/pith/CU5U5T6FGP3KJS6S32K6RHFU4H/action/replication_record"}},"created_at":"2026-07-05T08:54:04.375538+00:00","updated_at":"2026-07-05T08:54:04.375538+00:00"}