{"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/noisy-channel-language-model-prompting-for","title":"Noisy Channel Language Model Prompting for Few-Shot Text Classification","arxiv_id":"2108.04106","date":"2021-08-09","proceeding":"ACL 2022 5","authors":["Sewon Min","Mike Lewis","Hannaneh Hajishirzi","Luke Zettlemoyer"],"abstract":"We introduce a noisy channel approach for language model prompting in few-shot text classification. Instead of computing the likelihood of the label given the input (referred as direct models), channel models compute the conditional probability of the input given the label, and are thereby required to explain every word in the input. We use channel models for recently proposed few-shot learning methods with no or very limited updates to the language model parameters, via either in-context demonstration or prompt tuning. Our experiments show that, for both methods, channel models significantly outperform their direct counterparts, which we attribute to their stability, i.e., lower variance and higher worst-case accuracy. We also present extensive ablations that provide recommendations for when to use channel prompt tuning instead of other competitive methods (e.g., direct head tuning): channel prompt tuning is preferred when the number of training examples is small, labels in the training data are imbalanced, or generalization to unseen labels is required.","url_abs":"https://arxiv.org/abs/2108.04106v3","url_pdf":"https://arxiv.org/pdf/2108.04106v3.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":"noisy-channel-language-model-prompting-for","repo_url":"https://github.com/shmsw25/Channel-LM-Prompting","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"attribute","task_name":"Attribute"},{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"few-shot-learning","task_name":"Few-Shot Learning"},{"task_slug":"few-shot-text-classification","task_name":"Few-Shot Text Classification"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"text-classification","task_name":"Text Classification"},{"task_slug":"text-classification-1","task_name":"text-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2108.04106","atlas_url":"https://app.syntology.ai/?focus=2108.04106","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.04106"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/shmsw25/Channel-LM-Prompting","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":3},"by_repo_kind":{"official":{"samples":3,"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":3,"samples":[{"code_sha256_prefix":"126ae8eeb63d59bf","entry":"get_label","repo":"shmsw25/Channel-LM-Prompting","repo_kind":"official","path":"generate_k_shot_data.py","file_url":"https://github.com/shmsw25/Channel-LM-Prompting/blob/HEAD/generate_k_shot_data.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"126ae8eeb63d59bf"}},{"code_sha256_prefix":"8e27652a29c8adcc","entry":"load_datasets","repo":"shmsw25/Channel-LM-Prompting","repo_kind":"official","path":"generate_k_shot_data.py","file_url":"https://github.com/shmsw25/Channel-LM-Prompting/blob/HEAD/generate_k_shot_data.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8e27652a29c8adcc"}},{"code_sha256_prefix":"efd1b7718b950470","entry":"split_header","repo":"shmsw25/Channel-LM-Prompting","repo_kind":"official","path":"generate_k_shot_data.py","file_url":"https://github.com/shmsw25/Channel-LM-Prompting/blob/HEAD/generate_k_shot_data.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"efd1b7718b950470"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}