{"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/surface-form-competition-why-the-highest","title":"Surface Form Competition: Why the Highest Probability Answer Isn't Always Right","arxiv_id":"2104.08315","date":"2021-04-16","proceeding":null,"authors":["Ari Holtzman","Peter West","Vered Shwartz","Yejin Choi","Luke Zettlemoyer"],"abstract":"Large language models have shown promising results in zero-shot settings (Brown et al.,2020; Radford et al., 2019). For example, they can perform multiple choice tasks simply by conditioning on a question and selecting the answer with the highest probability. However, ranking by string probability can be problematic due to surface form competition-wherein different surface forms compete for probability mass, even if they represent the same underlying concept, e.g. \"computer\" and \"PC.\" Since probability mass is finite, this lowers the probability of the correct answer, due to competition from other strings that are valid answers (but not one of the multiple choice options). We introduce Domain Conditional Pointwise Mutual Information, an alternative scoring function that directly compensates for surface form competition by simply reweighing each option according to a term that is proportional to its a priori likelihood within the context of the specific zero-shot task. It achieves consistent gains in zero-shot performance over both calibrated (Zhao et al., 2021) and uncalibrated scoring functions on all GPT-2 and GPT-3 models over a variety of multiple choice datasets.","url_abs":"https://arxiv.org/abs/2104.08315v9","url_pdf":"https://arxiv.org/pdf/2104.08315v9.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":"surface-form-competition-why-the-highest","repo_url":"https://github.com/peterwestuw/surface-form-competition","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"surface-form-competition-why-the-highest","repo_url":"https://github.com/soheeyang/unified-prompt-selection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"form","task_name":"Form"},{"task_slug":"multiple-choice","task_name":"Multiple-choice"},{"task_slug":null,"task_name":"valid"}],"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-2","method_name":"GPT-2"},{"method_slug":"gpt-3","method_name":"GPT-3"},{"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":{"atlas_url":"https://app.syntology.ai/?focus=2104.08315","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.08315"}},"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/peterwestuw/surface-form-competition","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/soheeyang/unified-prompt-selection","reach":null}],"summary":{"ran_draft_wrong":3,"ran_fixture":2},"by_repo_kind":{"listed":{"samples":5,"ran":5,"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":"e7db1894951b31f1","entry":"_mean_normalize_prob","repo":"soheeyang/unified-prompt-selection","repo_kind":"listed","path":"method/calibration.py","file_url":"https://github.com/soheeyang/unified-prompt-selection/blob/HEAD/method/calibration.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e7db1894951b31f1"}},{"code_sha256_prefix":"57ac2724e40f23c9","entry":"calibrate_pmi","repo":"soheeyang/unified-prompt-selection","repo_kind":"listed","path":"method/calibration.py","file_url":"https://github.com/soheeyang/unified-prompt-selection/blob/HEAD/method/calibration.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"57ac2724e40f23c9"}},{"code_sha256_prefix":"12307150c8caecad","entry":"get_normalized_probs_from_logprob","repo":"soheeyang/unified-prompt-selection","repo_kind":"listed","path":"method/calibration.py","file_url":"https://github.com/soheeyang/unified-prompt-selection/blob/HEAD/method/calibration.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"12307150c8caecad"}},{"code_sha256_prefix":"eafc673b3e425c4d","entry":"normalize_prob","repo":"soheeyang/unified-prompt-selection","repo_kind":"listed","path":"method/calibration.py","file_url":"https://github.com/soheeyang/unified-prompt-selection/blob/HEAD/method/calibration.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"eafc673b3e425c4d"}},{"code_sha256_prefix":"6def77c0d0f72096","entry":"safe_log","repo":"soheeyang/unified-prompt-selection","repo_kind":"listed","path":"method/calibration.py","file_url":"https://github.com/soheeyang/unified-prompt-selection/blob/HEAD/method/calibration.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6def77c0d0f72096"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}