{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/say-more-with-less-understanding-prompt","title":"Say More with Less: Understanding Prompt Learning Behaviors through Gist Compression","arxiv_id":"2402.16058","date":"2024-02-25","proceeding":null,"authors":["Xinze Li","Zhenghao Liu","Chenyan Xiong","Shi Yu","Yukun Yan","Shuo Wang","Ge Yu"],"abstract":"Large language models (LLMs) require lengthy prompts as the input context to produce output aligned with user intentions, a process that incurs extra costs during inference. In this paper, we propose the Gist COnditioned deCOding (Gist-COCO) model, introducing a novel method for compressing prompts which also can assist the prompt interpretation and engineering. Gist-COCO employs an encoder-decoder based language model and then incorporates an additional encoder as a plugin module to compress prompts with inputs using gist tokens. It finetunes the compression plugin module and uses the representations of gist tokens to emulate the raw prompts in the vanilla language model. By verbalizing the representations of gist tokens into gist prompts, the compression ability of Gist-COCO can be generalized to different LLMs with high compression rates. Our experiments demonstrate that Gist-COCO outperforms previous prompt compression models in both passage and instruction compression tasks. Further analysis on gist verbalization results suggests that our gist prompts serve different functions in aiding language models. They may directly provide potential answers, generate the chain-of-thought, or simply repeat the inputs. All data and codes are available at https://github.com/OpenMatch/Gist-COCO .","url_abs":"https://arxiv.org/abs/2402.16058v1","url_pdf":"https://arxiv.org/pdf/2402.16058v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"say-more-with-less-understanding-prompt","repo_url":"https://github.com/openmatch/gist-coco","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"prompt-learning","task_name":"Prompt Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2402.16058","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.16058"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/openmatch/gist-coco","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":2,"unverified":1},"by_repo_kind":{"official":{"samples":3,"ran":2,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"185759d79e24efed","entry":"call_model","repo":"openmatch/gist-coco","repo_kind":"official","path":"src/inference/generalize/get_generalize_instruction_data.py","file_url":"https://github.com/openmatch/gist-coco/blob/HEAD/src/inference/generalize/get_generalize_instruction_data.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"185759d79e24efed"}},{"code_sha256_prefix":"bf0ba2f1b79267f8","entry":"get_gold_answers","repo":"openmatch/gist-coco","repo_kind":"official","path":"src/inference/plug/flan-t5-compression-passage.py","file_url":"https://github.com/openmatch/gist-coco/blob/HEAD/src/inference/plug/flan-t5-compression-passage.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bf0ba2f1b79267f8"}},{"code_sha256_prefix":"85f31f5811b9b51a","entry":"postprocess_text","repo":"openmatch/gist-coco","repo_kind":"official","path":"src/inference/generalize/get_generalize_instruction_data.py","file_url":"https://github.com/openmatch/gist-coco/blob/HEAD/src/inference/generalize/get_generalize_instruction_data.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"85f31f5811b9b51a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}