{"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/rectifying-demonstration-shortcut-in-in","title":"Rectifying Demonstration Shortcut in In-Context Learning","arxiv_id":"2403.09488","date":"2024-03-14","proceeding":null,"authors":["Joonwon Jang","Sanghwan Jang","Wonbin Kweon","Minjin Jeon","Hwanjo Yu"],"abstract":"Large language models (LLMs) are able to solve various tasks with only a few demonstrations utilizing their in-context learning (ICL) abilities. However, LLMs often rely on their pre-trained semantic priors of demonstrations rather than on the input-label relationships to proceed with ICL prediction. In this work, we term this phenomenon as the 'Demonstration Shortcut'. While previous works have primarily focused on improving ICL prediction results for predefined tasks, we aim to rectify the Demonstration Shortcut, thereby enabling the LLM to effectively learn new input-label relationships from demonstrations. To achieve this, we introduce In-Context Calibration, a demonstration-aware calibration method. We evaluate the effectiveness of the proposed method in two settings: (1) the Original ICL Task using the standard label space and (2) the Task Learning setting, where the label space is replaced with semantically unrelated tokens. In both settings, In-Context Calibration demonstrates substantial improvements, with results generalized across three LLM families (OPT, GPT, and Llama2) under various configurations.","url_abs":"https://arxiv.org/abs/2403.09488v3","url_pdf":"https://arxiv.org/pdf/2403.09488v3.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":"rectifying-demonstration-shortcut-in-in","repo_url":"https://github.com/lainshower/in-context-calibration","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"in-context-learning","task_name":"In-Context Learning"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"cosine-annealing","method_name":"Cosine Annealing"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"discriminative-fine-tuning","method_name":"Discriminative Fine-Tuning"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"gpt","method_name":"GPT"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-cosine-annealing","method_name":"Linear Warmup With Cosine Annealing"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2403.09488","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.09488"}},"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/lainshower/in-context-calibration","reach":null}],"summary":{"ran_honours":1,"ran_draft_wrong":2,"unverified":6},"by_repo_kind":{"official":{"samples":9,"ran":3,"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":9,"samples":[{"code_sha256_prefix":"76931defc8580476","entry":"chunk_size_helper","repo":"lainshower/in-context-calibration","repo_kind":"official","path":"utils.py","file_url":"https://github.com/lainshower/in-context-calibration/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"76931defc8580476"}},{"code_sha256_prefix":"bdf1c41b44f672f1","entry":"chunks","repo":"lainshower/in-context-calibration","repo_kind":"official","path":"utils.py","file_url":"https://github.com/lainshower/in-context-calibration/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"bdf1c41b44f672f1"}},{"code_sha256_prefix":"e37bbdf75acd586c","entry":"construct_prompt","repo":"lainshower/in-context-calibration","repo_kind":"official","path":"utils.py","file_url":"https://github.com/lainshower/in-context-calibration/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e37bbdf75acd586c"}},{"code_sha256_prefix":"49196c172c60c041","entry":"complete","repo":"lainshower/in-context-calibration","repo_kind":"official","path":"utils.py","file_url":"https://github.com/lainshower/in-context-calibration/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"49196c172c60c041"}},{"code_sha256_prefix":"50f02fdb39cbb530","entry":"complete_gpt2","repo":"lainshower/in-context-calibration","repo_kind":"official","path":"utils.py","file_url":"https://github.com/lainshower/in-context-calibration/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"50f02fdb39cbb530"}},{"code_sha256_prefix":"b5797bb0c80ce893","entry":"complete_gpt3","repo":"lainshower/in-context-calibration","repo_kind":"official","path":"utils.py","file_url":"https://github.com/lainshower/in-context-calibration/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b5797bb0c80ce893"}},{"code_sha256_prefix":"b18ccaa5f7df5e9f","entry":"get_model_response","repo":"lainshower/in-context-calibration","repo_kind":"official","path":"utils.py","file_url":"https://github.com/lainshower/in-context-calibration/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b18ccaa5f7df5e9f"}},{"code_sha256_prefix":"cdfcb2d8e8a5acda","entry":"setup_gpt2","repo":"lainshower/in-context-calibration","repo_kind":"official","path":"utils.py","file_url":"https://github.com/lainshower/in-context-calibration/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"cdfcb2d8e8a5acda"}},{"code_sha256_prefix":"2224bc9059d64ea5","entry":"setup_gpt3","repo":"lainshower/in-context-calibration","repo_kind":"official","path":"utils.py","file_url":"https://github.com/lainshower/in-context-calibration/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2224bc9059d64ea5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}