{"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/why-exposure-bias-matters-an-imitation","title":"Why Exposure Bias Matters: An Imitation Learning Perspective of Error Accumulation in Language Generation","arxiv_id":"2204.01171","date":"2022-04-03","proceeding":"Findings (ACL) 2022 5","authors":["Kushal Arora","Layla El Asri","Hareesh Bahuleyan","Jackie Chi Kit Cheung"],"abstract":"Current language generation models suffer from issues such as repetition, incoherence, and hallucinations. An often-repeated hypothesis is that this brittleness of generation models is caused by the training and the generation procedure mismatch, also referred to as exposure bias. In this paper, we verify this hypothesis by analyzing exposure bias from an imitation learning perspective. We show that exposure bias leads to an accumulation of errors, analyze why perplexity fails to capture this accumulation, and empirically show that this accumulation results in poor generation quality. Source code to reproduce these experiments is available at https://github.com/kushalarora/quantifying_exposure_bias","url_abs":"https://arxiv.org/abs/2204.01171v3","url_pdf":"https://arxiv.org/pdf/2204.01171v3.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":"why-exposure-bias-matters-an-imitation","repo_url":"https://github.com/kushalarora/quantifying_exposure_bias","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"imitation-learning","task_name":"Imitation Learning"},{"task_slug":"text-generation","task_name":"Text Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2204.01171","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.01171"}},"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/kushalarora/quantifying_exposure_bias","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":4},"by_repo_kind":{"official":{"samples":4,"ran":0,"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":"8a0fcb322a884bdf","entry":"generate_list","repo":"kushalarora/quantifying_exposure_bias","repo_kind":"official","path":"quant_exp_bias/commands/quantify_exposure_bias_pretrained.py","file_url":"https://github.com/kushalarora/quantifying_exposure_bias/blob/HEAD/quant_exp_bias/commands/quantify_exposure_bias_pretrained.py","link_basis":"harvester_set","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":"8a0fcb322a884bdf"}},{"code_sha256_prefix":"159431fbc9468675","entry":"get_mean_std_results","repo":"kushalarora/quantifying_exposure_bias","repo_kind":"official","path":"decoding_experiments.py","file_url":"https://github.com/kushalarora/quantifying_exposure_bias/blob/HEAD/decoding_experiments.py","link_basis":"harvester_set","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":"159431fbc9468675"}},{"code_sha256_prefix":"78547cca84bfae83","entry":"ngram_metrics","repo":"kushalarora/quantifying_exposure_bias","repo_kind":"official","path":"quant_exp_bias/metrics/exposure_bias.py","file_url":"https://github.com/kushalarora/quantifying_exposure_bias/blob/HEAD/quant_exp_bias/metrics/exposure_bias.py","link_basis":"harvester_set","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":"78547cca84bfae83"}},{"code_sha256_prefix":"b8c2bcd9e75d4e4a","entry":"repeat_at_1","repo":"kushalarora/quantifying_exposure_bias","repo_kind":"official","path":"quant_exp_bias/metrics/exposure_bias.py","file_url":"https://github.com/kushalarora/quantifying_exposure_bias/blob/HEAD/quant_exp_bias/metrics/exposure_bias.py","link_basis":"harvester_set","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":"b8c2bcd9e75d4e4a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}