{"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/answer-is-all-you-need-instruction-following","title":"Answer is All You Need: Instruction-following Text Embedding via Answering the Question","arxiv_id":"2402.09642","date":"2024-02-15","proceeding":null,"authors":["Letian Peng","Yuwei Zhang","Zilong Wang","Jayanth Srinivasa","Gaowen Liu","Zihan Wang","Jingbo Shang"],"abstract":"This work aims to build a text embedder that can capture characteristics of texts specified by user instructions. Despite its tremendous potential to deploy user-oriented embeddings, none of previous approaches provides a concrete solution for it. This paper offers a new viewpoint, which treats the instruction as a question about the input text and encodes the expected answers to obtain the representation accordingly. Intuitively, texts with the same (implicit) semantics would share similar answers following the instruction, thus leading to more similar embeddings. Specifically, we propose InBedder that instantiates this embed-via-answering idea by only fine-tuning language models on abstractive question answering tasks. InBedder demonstrates significantly improved instruction-following capabilities according to our proposed instruction awareness tests and instruction robustness tests, when applied to both large language models (LLMs) (e.g., llama-2-7b) and smaller encoder-based LMs (e.g., roberta-large). Additionally, our qualitative analysis of clustering outcomes, achieved by applying different instructions to the same corpus, demonstrates a high degree of interpretability.","url_abs":"https://arxiv.org/abs/2402.09642v1","url_pdf":"https://arxiv.org/pdf/2402.09642v1.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":"answer-is-all-you-need-instruction-following","repo_url":"https://github.com/zhang-yu-wei/inbedder","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"all","task_name":"All"},{"task_slug":"instruction-following","task_name":"Instruction Following"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":null,"task_name":"abstractive question answering"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2402.09642","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.09642"}},"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/zhang-yu-wei/inbedder","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":6,"ran_draft_wrong":1,"unverified":1},"by_repo_kind":{"official":{"samples":8,"ran":7,"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":"90710324cdd36fd8","entry":"batch_to_device","repo":"zhang-yu-wei/inbedder","repo_kind":"official","path":"lm_encoders_hf/causallm_encoder_hf.py","file_url":"https://github.com/zhang-yu-wei/inbedder/blob/HEAD/lm_encoders_hf/causallm_encoder_hf.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":"90710324cdd36fd8"}},{"code_sha256_prefix":"8ad67018fc3afcbf","entry":"calculate_entropy_numpy","repo":"zhang-yu-wei/inbedder","repo_kind":"official","path":"gather_cluster_results.py","file_url":"https://github.com/zhang-yu-wei/inbedder/blob/HEAD/gather_cluster_results.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":"8ad67018fc3afcbf"}},{"code_sha256_prefix":"d07d04439cd1d44f","entry":"jload","repo":"zhang-yu-wei/inbedder","repo_kind":"official","path":"alpaca_train/utils.py","file_url":"https://github.com/zhang-yu-wei/inbedder/blob/HEAD/alpaca_train/utils.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d07d04439cd1d44f"}},{"code_sha256_prefix":"2fc8e8a879ef10da","entry":"verify_output_value","repo":"zhang-yu-wei/inbedder","repo_kind":"official","path":"lm_encoders_hf/causallm_encoder_hf.py","file_url":"https://github.com/zhang-yu-wei/inbedder/blob/HEAD/lm_encoders_hf/causallm_encoder_hf.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":"2fc8e8a879ef10da"}},{"code_sha256_prefix":"e1de4494812c69f8","entry":"verify_output_value","repo":"zhang-yu-wei/inbedder","repo_kind":"official","path":"lm_encoders_hf/causallm_reencode_multiple.py","file_url":"https://github.com/zhang-yu-wei/inbedder/blob/HEAD/lm_encoders_hf/causallm_reencode_multiple.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":"e1de4494812c69f8"}},{"code_sha256_prefix":"a97dd7156c806584","entry":"verify_output_value","repo":"zhang-yu-wei/inbedder","repo_kind":"official","path":"lm_encoders_hf/maskedlm_encoder_hf.py","file_url":"https://github.com/zhang-yu-wei/inbedder/blob/HEAD/lm_encoders_hf/maskedlm_encoder_hf.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":"a97dd7156c806584"}},{"code_sha256_prefix":"8f6ca7acfe69acd9","entry":"verify_output_value","repo":"zhang-yu-wei/inbedder","repo_kind":"official","path":"lm_encoders_hf/seq2seqlm_encoder_hf.py","file_url":"https://github.com/zhang-yu-wei/inbedder/blob/HEAD/lm_encoders_hf/seq2seqlm_encoder_hf.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":"8f6ca7acfe69acd9"}},{"code_sha256_prefix":"10c571286b5bd954","entry":"read_from_hub","repo":"zhang-yu-wei/inbedder","repo_kind":"official","path":"alpaca_train/utils.py","file_url":"https://github.com/zhang-yu-wei/inbedder/blob/HEAD/alpaca_train/utils.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":"10c571286b5bd954"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}