{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/measuring-and-narrowing-the-compositionality","title":"Measuring and Narrowing the Compositionality Gap in Language Models","arxiv_id":"2210.03350","date":"2022-10-07","proceeding":null,"authors":["Ofir Press","Muru Zhang","Sewon Min","Ludwig Schmidt","Noah A. Smith","Mike Lewis"],"abstract":"We investigate the ability of language models to perform compositional reasoning tasks where the overall solution depends on correctly composing the answers to sub-problems. We measure how often models can correctly answer all sub-problems but not generate the overall solution, a ratio we call the compositionality gap. We evaluate this ratio by asking multi-hop questions with answers that require composing multiple facts unlikely to have been observed together during pretraining. In the GPT-3 family of models, as model size increases we show that the single-hop question answering performance improves faster than the multi-hop performance does, therefore the compositionality gap does not decrease. This surprising result suggests that while more powerful models memorize and recall more factual knowledge, they show no corresponding improvement in their ability to perform this kind of compositional reasoning. We then demonstrate how elicitive prompting (such as chain of thought) narrows the compositionality gap by reasoning explicitly. We present a new method, self-ask, that further improves on chain of thought. In our method, the model explicitly asks itself (and answers) follow-up questions before answering the initial question. We finally show that self-ask's structured prompting lets us easily plug in a search engine to answer the follow-up questions, which additionally improves accuracy.","url_abs":"https://arxiv.org/abs/2210.03350v3","url_pdf":"https://arxiv.org/pdf/2210.03350v3.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":"measuring-and-narrowing-the-compositionality","repo_url":"https://github.com/ofirpress/self-ask","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"question-answering","task_name":"Question Answering"}],"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":"dropout","method_name":"Dropout"},{"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":[{"slug":"bamboogle","name":"Bamboogle","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/question-answering-on-bamboogle","task":"Question Answering","dataset":"Bamboogle","model":"Self-ask (GPT-3; davinci-002) + Google Search","rank_in_archive_order":4,"of":9,"metrics":{"Accuracy":"60.0"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-bamboogle","task":"Question Answering","dataset":"Bamboogle","model":"Self-ask (GPT-3; davinci-002)","rank_in_archive_order":5,"of":9,"metrics":{"Accuracy":"57.6"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-bamboogle","task":"Question Answering","dataset":"Bamboogle","model":"Chain-of-Thought (GPT-3; davinci-002)","rank_in_archive_order":6,"of":9,"metrics":{"Accuracy":"46.4"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-bamboogle","task":"Question Answering","dataset":"Bamboogle","model":"Direct Prompting (GPT-3; davinci-002)","rank_in_archive_order":8,"of":9,"metrics":{"Accuracy":"17.6"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-bamboogle","task":"Question Answering","dataset":"Bamboogle","model":"Google Search","rank_in_archive_order":9,"of":9,"metrics":{"Accuracy":"0"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-fever","task":"Question Answering","dataset":"FEVER","model":"Self-Ask","rank_in_archive_order":2,"of":8,"metrics":{"EM":"64.2"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-webquestions","task":"Question Answering","dataset":"WebQuestions","model":"Self-Ask","rank_in_archive_order":23,"of":37,"metrics":{"EM":"31.1"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2210.03350","atlas_url":"https://app.syntology.ai/?focus=2210.03350","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2210.03350"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2210.03350\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2210.03350"},"call":"get_concepts_for_paper(arxiv_id=\"2210.03350\")"}],"by_repo":[{"repo":"ofirpress/self-ask","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"d8c37daf3d0e7ea658a21ea38c805af50c3ee8aefba86974bf394c6ba78991b2","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}