{"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/large-language-models-are-not-zero-shot","title":"The Goldilocks of Pragmatic Understanding: Fine-Tuning Strategy Matters for Implicature Resolution by LLMs","arxiv_id":"2210.14986","date":"2022-10-26","proceeding":"NeurIPS 2023 11","authors":["Laura Ruis","Akbir Khan","Stella Biderman","Sara Hooker","Tim Rocktäschel","Edward Grefenstette"],"abstract":"Despite widespread use of LLMs as conversational agents, evaluations of performance fail to capture a crucial aspect of communication: interpreting language in context -- incorporating its pragmatics. Humans interpret language using beliefs and prior knowledge about the world. For example, we intuitively understand the response \"I wore gloves\" to the question \"Did you leave fingerprints?\" as meaning \"No\". To investigate whether LLMs have the ability to make this type of inference, known as an implicature, we design a simple task and evaluate four categories of widely used state-of-the-art models. We find that, despite only evaluating on utterances that require a binary inference (yes or no), models in three of these categories perform close to random. However, LLMs instruction-tuned at the example-level perform significantly better. These results suggest that certain fine-tuning strategies are far better at inducing pragmatic understanding in models. We present our findings as the starting point for further research into evaluating how LLMs interpret language in context and to drive the development of more pragmatic and useful models of human discourse.","url_abs":"https://arxiv.org/abs/2210.14986v2","url_pdf":"https://arxiv.org/pdf/2210.14986v2.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":"large-language-models-are-not-zero-shot","repo_url":"https://github.com/lauraruis/do-pigs-fly","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[],"methods":[{"method_slug":"fail","method_name":"fail"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2210.14986","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.14986"}},"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":"deterministic:regex_extraction","url":"https://github.com/LauraRuis/do-pigs-fly","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lauraruis/do-pigs-fly","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":2},"by_repo_kind":{"official":{"samples":2,"ran":2,"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":2,"samples":[{"code_sha256_prefix":"e5aa779dd06543c5","entry":"parse_aggregated_results","repo":"LauraRuis/do-pigs-fly","repo_kind":"official","path":"src/error_analysis.py","file_url":"https://github.com/LauraRuis/do-pigs-fly/blob/HEAD/src/error_analysis.py","link_basis":"first_harvest_node","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":"e5aa779dd06543c5"}},{"code_sha256_prefix":"2c0c6a20b597c244","entry":"parse_slim_file","repo":"LauraRuis/do-pigs-fly","repo_kind":"official","path":"src/error_analysis.py","file_url":"https://github.com/LauraRuis/do-pigs-fly/blob/HEAD/src/error_analysis.py","link_basis":"first_harvest_node","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":"2c0c6a20b597c244"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}