{"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":"/task/natural-language-understanding/papers/4","list_of":"/task/natural-language-understanding","task":"Natural Language Understanding","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":4,"pages_in_order":20,"rows_per_page":100,"rows":[301,400],"of":1978,"counts":{"archive_papers_tagged":1978,"with_a_code_link":809,"where_syntology_ran_a_sample":185,"not_listed_spam_title":0,"listed":1978,"listed_where_code_ran":185,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":155,"every_run_a_failure_of_syntologys_instrument":30,"listed_with_a_run_with_no_instrument_failure":155,"listed_every_run_a_failure_of_syntologys_instrument":30,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/natural-language-understanding","prev":"/task/natural-language-understanding/papers/3","next":"/task/natural-language-understanding/papers/5","papers":[{"url":"/paper/structured-probabilistic-coding","slug":"structured-probabilistic-coding","title":"Structured Probabilistic Coding","date":"2023-12-21","arxiv_id":"2312.13933","repositories_listed":1,"syntology":null},{"url":"/paper/imitation-of-life-a-search-engine-for","slug":"imitation-of-life-a-search-engine-for","title":"Imitation of Life: A Search Engine for Biologically Inspired Design","date":"2023-12-20","arxiv_id":"2312.12681","repositories_listed":1,"syntology":null},{"url":"/paper/consistentee-a-consistent-and-hardness-guided","slug":"consistentee-a-consistent-and-hardness-guided","title":"ConsistentEE: A Consistent and Hardness-Guided Early Exiting Method for Accelerating Language Models Inference","date":"2023-12-19","arxiv_id":"2312.11882","repositories_listed":1,"syntology":null},{"url":"/paper/bengali-intent-classification-with-generative","slug":"bengali-intent-classification-with-generative","title":"Bengali Intent Classification with Generative Adversarial BERT","date":"2023-12-17","arxiv_id":"2312.10679","repositories_listed":1,"syntology":null},{"url":"/paper/continuous-prompt-generation-from-linear","slug":"continuous-prompt-generation-from-linear","title":"Continuous Prompt Generation from Linear Combination of Discrete Prompt Embeddings","date":"2023-12-16","arxiv_id":"2312.10323","repositories_listed":1,"syntology":null},{"url":"/paper/bipft-binary-pre-trained-foundation","slug":"bipft-binary-pre-trained-foundation","title":"BiPFT: Binary Pre-trained Foundation Transformer with Low-rank Estimation of Binarization Residual Polynomials","date":"2023-12-14","arxiv_id":"2312.08937","repositories_listed":1,"syntology":null},{"url":"/paper/propres-investigating-the-projectivity-of","slug":"propres-investigating-the-projectivity-of","title":"PROPRES: Investigating the Projectivity of Presupposition with Various Triggers and Environments","date":"2023-12-14","arxiv_id":"2312.08755","repositories_listed":1,"syntology":null},{"url":"/paper/iekg-a-commonsense-knowledge-graph-for","slug":"iekg-a-commonsense-knowledge-graph-for","title":"IEKG: A Commonsense Knowledge Graph for Idiomatic Expressions","date":"2023-12-11","arxiv_id":"2312.06053","repositories_listed":1,"syntology":null},{"url":"/paper/a-study-on-the-calibration-of-in-context","slug":"a-study-on-the-calibration-of-in-context","title":"A Study on the Calibration of In-context Learning","date":"2023-12-07","arxiv_id":"2312.04021","repositories_listed":1,"syntology":{"n":17,"n_ran":9,"n_constructed":0,"n_ran_checked":7,"n_instrument":2,"n_unverified":8,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/a-study-on-the-calibration-of-in-context#ran","syntology_url":"https://syntology.ai/paper/2312.04021","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.04021"}},"official":{"repos":["hlzhang109/icl-calibration"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":8,"ran_from_kinds":["official"]}}},{"url":"/paper/improving-bias-mitigation-through-bias","slug":"improving-bias-mitigation-through-bias","title":"Improving Bias Mitigation through Bias Experts in Natural Language Understanding","date":"2023-12-06","arxiv_id":"2312.03577","repositories_listed":1,"syntology":null},{"url":"/paper/nlebench-norglm-a-comprehensive-empirical","slug":"nlebench-norglm-a-comprehensive-empirical","title":"NLEBench+NorGLM: A Comprehensive Empirical Analysis and Benchmark Dataset for Generative Language Models in Norwegian","date":"2023-12-03","arxiv_id":"2312.01314","repositories_listed":1,"syntology":{"n":4,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"0 ran · 4 unverified","sample_list":"/paper/nlebench-norglm-a-comprehensive-empirical#ran","syntology_url":"https://syntology.ai/paper/2312.01314","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.01314"}},"official":{"repos":["smartmedia-ai/norglm"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":[]}}},{"url":"/paper/summarization-based-data-augmentation-for","slug":"summarization-based-data-augmentation-for","title":"Summarization-based Data Augmentation for Document Classification","date":"2023-12-01","arxiv_id":"2312.00513","repositories_listed":1,"syntology":null},{"url":"/paper/taskweaver-a-code-first-agent-framework","slug":"taskweaver-a-code-first-agent-framework","title":"TaskWeaver: A Code-First Agent Framework","date":"2023-11-29","arxiv_id":"2311.17541","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/taskweaver-a-code-first-agent-framework#ran","syntology_url":"https://syntology.ai/paper/2311.17541","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.17541"}},"official":{"repos":["microsoft/taskweaver"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/sqatin-supervised-instruction-tuning-meets","slug":"sqatin-supervised-instruction-tuning-meets","title":"SQATIN: Supervised Instruction Tuning Meets Question Answering for Improved Dialogue NLU","date":"2023-11-16","arxiv_id":"2311.09502","repositories_listed":1,"syntology":null},{"url":"/paper/you-don-t-need-a-personality-test-to-know","slug":"you-don-t-need-a-personality-test-to-know","title":"You don't need a personality test to know these models are unreliable: Assessing the Reliability of Large Language Models on Psychometric Instruments","date":"2023-11-16","arxiv_id":"2311.09718","repositories_listed":1,"syntology":{"n":12,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":7,"n_pointer_only":12,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/you-don-t-need-a-personality-test-to-know#ran","syntology_url":"https://syntology.ai/paper/2311.09718","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.09718"}},"official":{"repos":["orange0629/llm-personas"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/maven-arg-completing-the-puzzle-of-all-in-one","slug":"maven-arg-completing-the-puzzle-of-all-in-one","title":"MAVEN-Arg: Completing the Puzzle of All-in-One Event Understanding Dataset with Event Argument Annotation","date":"2023-11-15","arxiv_id":"2311.09105","repositories_listed":1,"syntology":null},{"url":"/paper/xplainllm-a-qa-explanation-dataset-for","slug":"xplainllm-a-qa-explanation-dataset-for","title":"XplainLLM: A Knowledge-Augmented Dataset for Reliable Grounded Explanations in LLMs","date":"2023-11-15","arxiv_id":"2311.08614","repositories_listed":1,"syntology":null},{"url":"/paper/conic10k-a-challenging-math-problem","slug":"conic10k-a-challenging-math-problem","title":"Conic10K: A Challenging Math Problem Understanding and Reasoning Dataset","date":"2023-11-09","arxiv_id":"2311.05113","repositories_listed":1,"syntology":null},{"url":"/paper/distort-distract-decode-instruction-tuned","slug":"distort-distract-decode-instruction-tuned","title":"Instructive Decoding: Instruction-Tuned Large Language Models are Self-Refiner from Noisy Instructions","date":"2023-11-01","arxiv_id":"2311.00233","repositories_listed":1,"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"0 ran · 2 unverified","sample_list":"/paper/distort-distract-decode-instruction-tuned#ran","syntology_url":"https://syntology.ai/paper/2311.00233","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.00233"}},"official":{"repos":["joonkeekim/Instructive-Decoding"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"url":"/paper/dense-retrieval-as-indirect-supervision-for","slug":"dense-retrieval-as-indirect-supervision-for","title":"Dense Retrieval as Indirect Supervision for Large-space Decision Making","date":"2023-10-28","arxiv_id":"2310.18619","repositories_listed":1,"syntology":null},{"url":"/paper/tlm-token-level-masking-for-transformers","slug":"tlm-token-level-masking-for-transformers","title":"TLM: Token-Level Masking for Transformers","date":"2023-10-28","arxiv_id":"2310.18738","repositories_listed":1,"syntology":{"n":28,"n_ran":23,"n_constructed":0,"n_ran_checked":22,"n_instrument":1,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":22,"n_pointer_only":28,"phrase":"23 ran (of which 0 constructed an object rather than computing a result; 22 with no instrument failure: 0 honoured, 0 violated, 22 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/tlm-token-level-masking-for-transformers#ran","syntology_url":"https://syntology.ai/paper/2310.18738","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.18738"}},"official":{"repos":["young1993/tlm"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":3,"ran_from_kinds":["found_in_text","official"]}}},{"url":"/paper/large-language-models-are-temporal-and-causal","slug":"large-language-models-are-temporal-and-causal","title":"Large Language Models are Temporal and Causal Reasoners for Video Question Answering","date":"2023-10-24","arxiv_id":"2310.15747","repositories_listed":1,"syntology":{"n":4,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 4 unverified","sample_list":"/paper/large-language-models-are-temporal-and-causal#ran","syntology_url":"https://syntology.ai/paper/2310.15747","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.15747"}},"official":{"repos":["mlvlab/Flipped-VQA"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":[]}}},{"url":"/paper/tage-enabling-an-embodied-agent-to-understand","slug":"tage-enabling-an-embodied-agent-to-understand","title":"tagE: Enabling an Embodied Agent to Understand Human Instructions","date":"2023-10-24","arxiv_id":"2310.15605","repositories_listed":1,"syntology":null},{"url":"/paper/cof-cot-enhancing-large-language-models-with","slug":"cof-cot-enhancing-large-language-models-with","title":"CoF-CoT: Enhancing Large Language Models with Coarse-to-Fine Chain-of-Thought Prompting for Multi-domain NLU Tasks","date":"2023-10-23","arxiv_id":"2310.14623","repositories_listed":1,"syntology":null},{"url":"/paper/pre-trained-language-models-augmented-with","slug":"pre-trained-language-models-augmented-with","title":"Pre-Trained Language Models Augmented with Synthetic Scanpaths for Natural Language Understanding","date":"2023-10-23","arxiv_id":"2310.14676","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/pre-trained-language-models-augmented-with#ran","syntology_url":"https://syntology.ai/paper/2310.14676","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.14676"}},"official":{"repos":["aeye-lab/emnlp-syntheticscanpaths-nlu-pretrainedlm"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/explaining-interactions-between-text-spans","slug":"explaining-interactions-between-text-spans","title":"Explaining Interactions Between Text Spans","date":"2023-10-20","arxiv_id":"2310.13506","repositories_listed":1,"syntology":null},{"url":"/paper/primacy-effect-of-chatgpt","slug":"primacy-effect-of-chatgpt","title":"Primacy Effect of ChatGPT","date":"2023-10-20","arxiv_id":"2310.13206","repositories_listed":1,"syntology":null},{"url":"/paper/storyanalogy-deriving-story-level-analogies","slug":"storyanalogy-deriving-story-level-analogies","title":"StoryAnalogy: Deriving Story-level Analogies from Large Language Models to Unlock Analogical Understanding","date":"2023-10-19","arxiv_id":"2310.12874","repositories_listed":1,"syntology":null},{"url":"/paper/glore-evaluating-logical-reasoning-of-large","slug":"glore-evaluating-logical-reasoning-of-large","title":"GLoRE: Evaluating Logical Reasoning of Large Language Models","date":"2023-10-13","arxiv_id":"2310.09107","repositories_listed":1,"syntology":null},{"url":"/paper/split-and-denoise-protect-large-language","slug":"split-and-denoise-protect-large-language","title":"Split-and-Denoise: Protect large language model inference with local differential privacy","date":"2023-10-13","arxiv_id":"2310.09130","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/split-and-denoise-protect-large-language#ran","syntology_url":"https://syntology.ai/paper/2310.09130","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.09130"}},"official":{"repos":["nusioraprivacy/eaas-privacy"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/evaluating-the-effectiveness-of-capsule","slug":"evaluating-the-effectiveness-of-capsule","title":"Evaluating The Effectiveness of Capsule Neural Network in Toxic Comment Classification using Pre-trained BERT Embeddings","date":"2023-10-12","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/loftq-lora-fine-tuning-aware-quantization-for","slug":"loftq-lora-fine-tuning-aware-quantization-for","title":"LoftQ: LoRA-Fine-Tuning-Aware Quantization for Large Language Models","date":"2023-10-12","arxiv_id":"2310.08659","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/loftq-lora-fine-tuning-aware-quantization-for#ran","syntology_url":"https://syntology.ai/paper/2310.08659","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.08659"}},"official":{"repos":["yxli2123/loftq"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/phalm-building-a-knowledge-graph-from-scratch","slug":"phalm-building-a-knowledge-graph-from-scratch","title":"PHALM: Building a Knowledge Graph from Scratch by Prompting Humans and a Language Model","date":"2023-10-11","arxiv_id":"2310.07170","repositories_listed":1,"syntology":null},{"url":"/paper/compresso-structured-pruning-with","slug":"compresso-structured-pruning-with","title":"Compresso: Structured Pruning with Collaborative Prompting Learns Compact Large Language Models","date":"2023-10-08","arxiv_id":"2310.05015","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/compresso-structured-pruning-with#ran","syntology_url":"https://syntology.ai/paper/2310.05015","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.05015"}},"official":{"repos":["microsoft/moonlit"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/sea-sparse-linear-attention-with-estimated","slug":"sea-sparse-linear-attention-with-estimated","title":"SEA: Sparse Linear Attention with Estimated Attention Mask","date":"2023-10-03","arxiv_id":"2310.01777","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/sea-sparse-linear-attention-with-estimated#ran","syntology_url":"https://syntology.ai/paper/2310.01777","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.01777"}},"official":{"repos":["gmlwns2000/sea-attention"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/enigma-51-towards-a-fine-grained","slug":"enigma-51-towards-a-fine-grained","title":"ENIGMA-51: Towards a Fine-Grained Understanding of Human-Object Interactions in Industrial Scenarios","date":"2023-09-26","arxiv_id":"2309.14809","repositories_listed":1,"syntology":null},{"url":"/paper/acegpt-localizing-large-language-models-in","slug":"acegpt-localizing-large-language-models-in","title":"AceGPT, Localizing Large Language Models in Arabic","date":"2023-09-21","arxiv_id":"2309.12053","repositories_listed":1,"syntology":null},{"url":"/paper/implicit-differentiable-outlier-detection","slug":"implicit-differentiable-outlier-detection","title":"Implicit Differentiable Outlier Detection Enable Robust Deep Multimodal Analysis","date":"2023-09-21","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/metamath-bootstrap-your-own-mathematical","slug":"metamath-bootstrap-your-own-mathematical","title":"MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models","date":"2023-09-21","arxiv_id":"2309.12284","repositories_listed":1,"syntology":{"n":22,"n_ran":15,"n_constructed":0,"n_ran_checked":1,"n_instrument":14,"n_unverified":7,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 14 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/metamath-bootstrap-your-own-mathematical#ran","syntology_url":"https://syntology.ai/paper/2309.12284","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.12284"}},"official":{"repos":["meta-math/MetaMath"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/sequence-to-sequence-spanish-pre-trained","slug":"sequence-to-sequence-spanish-pre-trained","title":"Sequence-to-Sequence Spanish Pre-trained Language Models","date":"2023-09-20","arxiv_id":"2309.11259","repositories_listed":1,"syntology":null},{"url":"/paper/natural-language-embedded-programs-for-hybrid","slug":"natural-language-embedded-programs-for-hybrid","title":"Natural Language Embedded Programs for Hybrid Language Symbolic Reasoning","date":"2023-09-19","arxiv_id":"2309.10814","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/natural-language-embedded-programs-for-hybrid#ran","syntology_url":"https://syntology.ai/paper/2309.10814","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.10814"}},"official":{"repos":["luohongyin/langcode"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/llm4jobs-unsupervised-occupation-extraction","slug":"llm4jobs-unsupervised-occupation-extraction","title":"LLM4Jobs: Unsupervised occupation extraction and standardization leveraging Large Language Models","date":"2023-09-18","arxiv_id":"2309.09708","repositories_listed":1,"syntology":null},{"url":"/paper/long-range-transformer-architectures-for","slug":"long-range-transformer-architectures-for","title":"Long-Range Transformer Architectures for Document Understanding","date":"2023-09-11","arxiv_id":"2309.05503","repositories_listed":1,"syntology":null},{"url":"/paper/chatgpt-as-data-augmentation-for","slug":"chatgpt-as-data-augmentation-for","title":"ChatGPT as Data Augmentation for Compositional Generalization: A Case Study in Open Intent Detection","date":"2023-08-25","arxiv_id":"2308.13517","repositories_listed":1,"syntology":null},{"url":"/paper/seqgpt-an-out-of-the-box-large-language-model","slug":"seqgpt-an-out-of-the-box-large-language-model","title":"SeqGPT: An Out-of-the-box Large Language Model for Open Domain Sequence Understanding","date":"2023-08-21","arxiv_id":"2308.10529","repositories_listed":1,"syntology":null},{"url":"/paper/hicl-hashtag-driven-in-context-learning-for","slug":"hicl-hashtag-driven-in-context-learning-for","title":"HICL: Hashtag-Driven In-Context Learning for Social Media Natural Language Understanding","date":"2023-08-19","arxiv_id":"2308.09985","repositories_listed":1,"syntology":null},{"url":"/paper/mindmap-knowledge-graph-prompting-sparks","slug":"mindmap-knowledge-graph-prompting-sparks","title":"MindMap: Knowledge Graph Prompting Sparks Graph of Thoughts in Large Language Models","date":"2023-08-17","arxiv_id":"2308.09729","repositories_listed":1,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":8,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/mindmap-knowledge-graph-prompting-sparks#ran","syntology_url":"https://syntology.ai/paper/2308.09729","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.09729"}},"official":{"repos":["wyl-willing/MindMap"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/mddial-a-multi-turn-differential-diagnosis","slug":"mddial-a-multi-turn-differential-diagnosis","title":"MDDial: A Multi-turn Differential Diagnosis Dialogue Dataset with Reliability Evaluation","date":"2023-08-16","arxiv_id":"2308.08147","repositories_listed":1,"syntology":null},{"url":"/paper/token-scaled-logit-distillation-for-ternary-1","slug":"token-scaled-logit-distillation-for-ternary-1","title":"Token-Scaled Logit Distillation for Ternary Weight Generative Language Models","date":"2023-08-13","arxiv_id":"2308.06744","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/token-scaled-logit-distillation-for-ternary-1#ran","syntology_url":"https://syntology.ai/paper/2308.06744","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.06744"}},"official":{"repos":["aiha-lab/tsld"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/metacognitive-prompting-improves","slug":"metacognitive-prompting-improves","title":"Metacognitive Prompting Improves Understanding in Large Language Models","date":"2023-08-10","arxiv_id":"2308.05342","repositories_listed":1,"syntology":null},{"url":"/paper/slot-induction-via-pre-trained-language-model","slug":"slot-induction-via-pre-trained-language-model","title":"Slot Induction via Pre-trained Language Model Probing and Multi-level Contrastive Learning","date":"2023-08-09","arxiv_id":"2308.04712","repositories_listed":1,"syntology":null},{"url":"/paper/baby-s-cothought-leveraging-large-language","slug":"baby-s-cothought-leveraging-large-language","title":"Baby's CoThought: Leveraging Large Language Models for Enhanced Reasoning in Compact Models","date":"2023-08-03","arxiv_id":"2308.01684","repositories_listed":1,"syntology":null},{"url":"/paper/dialogstudio-towards-richest-and-most-diverse","slug":"dialogstudio-towards-richest-and-most-diverse","title":"DialogStudio: Towards Richest and Most Diverse Unified Dataset Collection for Conversational AI","date":"2023-07-19","arxiv_id":"2307.10172","repositories_listed":1,"syntology":null},{"url":"/paper/ntk-approximating-mlp-fusion-for-efficient","slug":"ntk-approximating-mlp-fusion-for-efficient","title":"MLP Fusion: Towards Efficient Fine-tuning of Dense and Mixture-of-Experts Language Models","date":"2023-07-18","arxiv_id":"2307.08941","repositories_listed":1,"syntology":{"n":14,"n_ran":10,"n_constructed":5,"n_ran_checked":9,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":14,"phrase":"10 ran (of which 5 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/ntk-approximating-mlp-fusion-for-efficient#ran","syntology_url":"https://syntology.ai/paper/2307.08941","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.08941"}},"official":{"repos":["weitianxin/mlp_fusion"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":5,"n_ran_no_instrument_failure":9,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/is-prompt-based-finetuning-always-better-than","slug":"is-prompt-based-finetuning-always-better-than","title":"Is Prompt-Based Finetuning Always Better than Vanilla Finetuning? Insights from Cross-Lingual Language Understanding","date":"2023-07-15","arxiv_id":"2307.07880","repositories_listed":1,"syntology":null},{"url":"/paper/velma-verbalization-embodiment-of-llm-agents","slug":"velma-verbalization-embodiment-of-llm-agents","title":"VELMA: Verbalization Embodiment of LLM Agents for Vision and Language Navigation in Street View","date":"2023-07-12","arxiv_id":"2307.06082","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":6,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/velma-verbalization-embodiment-of-llm-agents#ran","syntology_url":"https://syntology.ai/paper/2307.06082","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.06082"}},"official":{"repos":["raphael-sch/velma"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/bluex-a-benchmark-based-on-brazilian-leading","slug":"bluex-a-benchmark-based-on-brazilian-leading","title":"BLUEX: A benchmark based on Brazilian Leading Universities Entrance eXams","date":"2023-07-11","arxiv_id":"2307.05410","repositories_listed":1,"syntology":null},{"url":"/paper/scriptworld-text-based-environment-for","slug":"scriptworld-text-based-environment-for","title":"ScriptWorld: Text Based Environment For Learning Procedural Knowledge","date":"2023-07-08","arxiv_id":"2307.03906","repositories_listed":1,"syntology":null},{"url":"/paper/distilling-large-vision-language-model-with","slug":"distilling-large-vision-language-model-with","title":"Distilling Large Vision-Language Model with Out-of-Distribution Generalizability","date":"2023-07-06","arxiv_id":"2307.03135","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/distilling-large-vision-language-model-with#ran","syntology_url":"https://syntology.ai/paper/2307.03135","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.03135"}},"official":{"repos":["xuanlinli17/large_vlm_distillation_ood"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/hegel-a-novel-dataset-for-geo-location-from","slug":"hegel-a-novel-dataset-for-geo-location-from","title":"HeGeL: A Novel Dataset for Geo-Location from Hebrew Text","date":"2023-07-02","arxiv_id":"2307.00509","repositories_listed":1,"syntology":null},{"url":"/paper/revisiting-sample-size-determination-in","slug":"revisiting-sample-size-determination-in","title":"Revisiting Sample Size Determination in Natural Language Understanding","date":"2023-07-01","arxiv_id":"2307.00374","repositories_listed":1,"syntology":null},{"url":"/paper/deep-language-networks-joint-prompt-training","slug":"deep-language-networks-joint-prompt-training","title":"Joint Prompt Optimization of Stacked LLMs using Variational Inference","date":"2023-06-21","arxiv_id":"2306.12509","repositories_listed":1,"syntology":{"n":19,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":16,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 16 unverified","sample_list":"/paper/deep-language-networks-joint-prompt-training#ran","syntology_url":"https://syntology.ai/paper/2306.12509","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.12509"}},"official":{"repos":["microsoft/deep-language-networks"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":16,"ran_from_kinds":["official"]}}},{"url":"/paper/training-transformers-with-4-bit-integers-1","slug":"training-transformers-with-4-bit-integers-1","title":"Training Transformers with 4-bit Integers","date":"2023-06-21","arxiv_id":"2306.11987","repositories_listed":1,"syntology":null},{"url":"/paper/adversarial-robustness-of-prompt-based-few","slug":"adversarial-robustness-of-prompt-based-few","title":"Adversarial Robustness of Prompt-based Few-Shot Learning for Natural Language Understanding","date":"2023-06-19","arxiv_id":"2306.11066","repositories_listed":1,"syntology":null},{"url":"/paper/data-selection-for-fine-tuning-large-language","slug":"data-selection-for-fine-tuning-large-language","title":"Data Selection for Fine-tuning Large Language Models Using Transferred Shapley Values","date":"2023-06-16","arxiv_id":"2306.10165","repositories_listed":1,"syntology":null},{"url":"/paper/bridging-the-gap-between-decision-and-logits","slug":"bridging-the-gap-between-decision-and-logits","title":"Bridging the Gap between Decision and Logits in Decision-based Knowledge Distillation for Pre-trained Language Models","date":"2023-06-15","arxiv_id":"2306.08909","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/bridging-the-gap-between-decision-and-logits#ran","syntology_url":"https://syntology.ai/paper/2306.08909","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.08909"}},"official":{"repos":["thunlp-mt/dbkd-plm"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/generate-to-understand-for-representation","slug":"generate-to-understand-for-representation","title":"Generate to Understand for Representation","date":"2023-06-14","arxiv_id":"2306.10056","repositories_listed":1,"syntology":null},{"url":"/paper/speechglue-how-well-can-self-supervised","slug":"speechglue-how-well-can-self-supervised","title":"SpeechGLUE: How Well Can Self-Supervised Speech Models Capture Linguistic Knowledge?","date":"2023-06-14","arxiv_id":"2306.08374","repositories_listed":1,"syntology":null},{"url":"/paper/deep-model-compression-also-helps-models","slug":"deep-model-compression-also-helps-models","title":"Deep Model Compression Also Helps Models Capture Ambiguity","date":"2023-06-12","arxiv_id":"2306.07061","repositories_listed":1,"syntology":null},{"url":"/paper/empowering-molecule-discovery-for-molecule","slug":"empowering-molecule-discovery-for-molecule","title":"Empowering Molecule Discovery for Molecule-Caption Translation with Large Language Models: A ChatGPT Perspective","date":"2023-06-11","arxiv_id":"2306.06615","repositories_listed":1,"syntology":null},{"url":"/paper/revisit-few-shot-intent-classification-with","slug":"revisit-few-shot-intent-classification-with","title":"Revisit Few-shot Intent Classification with PLMs: Direct Fine-tuning vs. Continual Pre-training","date":"2023-06-08","arxiv_id":"2306.05278","repositories_listed":1,"syntology":null},{"url":"/paper/logiqa-2-0-an-improved-dataset-for-logical","slug":"logiqa-2-0-an-improved-dataset-for-logical","title":"LogiQA 2.0—An Improved Dataset for Logical Reasoning in Natural Language Understanding","date":"2023-06-06","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-language-representation-with","slug":"enhancing-language-representation-with","title":"Enhancing Language Representation with Constructional Information for Natural Language Understanding","date":"2023-06-05","arxiv_id":"2306.02819","repositories_listed":1,"syntology":null},{"url":"/paper/a-simple-yet-effective-self-debiasing","slug":"a-simple-yet-effective-self-debiasing","title":"A Simple yet Effective Self-Debiasing Framework for Transformer Models","date":"2023-06-02","arxiv_id":"2306.01907","repositories_listed":1,"syntology":null},{"url":"/paper/a-template-independent-approach-for","slug":"a-template-independent-approach-for","title":"A template-independent approach for information extraction in real estate documents","date":"2023-05-30","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/preserving-pre-trained-features-helps","slug":"preserving-pre-trained-features-helps","title":"Preserving Pre-trained Features Helps Calibrate Fine-tuned Language Models","date":"2023-05-30","arxiv_id":"2305.19249","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/preserving-pre-trained-features-helps#ran","syntology_url":"https://syntology.ai/paper/2305.19249","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.19249"}},"official":{"repos":["thu-ml/lm-calibration"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/make-an-audio-2-temporal-enhanced-text-to","slug":"make-an-audio-2-temporal-enhanced-text-to","title":"Make-An-Audio 2: Temporal-Enhanced Text-to-Audio Generation","date":"2023-05-29","arxiv_id":"2305.18474","repositories_listed":1,"syntology":{"n":12,"n_ran":11,"n_constructed":0,"n_ran_checked":6,"n_instrument":5,"n_unverified":1,"n_honours":0,"n_violates":2,"n_no_contract":4,"n_pointer_only":5,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 2 violated, 4 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/make-an-audio-2-temporal-enhanced-text-to#ran","syntology_url":"https://syntology.ai/paper/2305.18474","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.18474"}},"official":null}},{"url":"/paper/robust-natural-language-understanding-with","slug":"robust-natural-language-understanding-with","title":"Robust Natural Language Understanding with Residual Attention Debiasing","date":"2023-05-28","arxiv_id":"2305.17627","repositories_listed":1,"syntology":null},{"url":"/paper/tri-level-joint-natural-language","slug":"tri-level-joint-natural-language","title":"Tri-level Joint Natural Language Understanding for Multi-turn Conversational Datasets","date":"2023-05-28","arxiv_id":"2305.17729","repositories_listed":1,"syntology":null},{"url":"/paper/a-unified-framework-for-slot-based-response","slug":"a-unified-framework-for-slot-based-response","title":"A Unified Framework for Slot based Response Generation in a Multimodal Dialogue System","date":"2023-05-27","arxiv_id":"2305.17433","repositories_listed":1,"syntology":null},{"url":"/paper/entailment-as-robust-self-learner","slug":"entailment-as-robust-self-learner","title":"Entailment as Robust Self-Learner","date":"2023-05-26","arxiv_id":"2305.17197","repositories_listed":1,"syntology":null},{"url":"/paper/merge-fast-private-text-generation","slug":"merge-fast-private-text-generation","title":"MERGE: Fast Private Text Generation","date":"2023-05-25","arxiv_id":"2305.15769","repositories_listed":1,"syntology":null},{"url":"/paper/cheap-and-quick-efficient-vision-language","slug":"cheap-and-quick-efficient-vision-language","title":"Cheap and Quick: Efficient Vision-Language Instruction Tuning for Large Language Models","date":"2023-05-24","arxiv_id":"2305.15023","repositories_listed":1,"syntology":null},{"url":"/paper/cream-visually-situated-natural-language","slug":"cream-visually-situated-natural-language","title":"Visually-Situated Natural Language Understanding with Contrastive Reading Model and Frozen Large Language Models","date":"2023-05-24","arxiv_id":"2305.15080","repositories_listed":1,"syntology":null},{"url":"/paper/csts-conditional-semantic-textual-similarity","slug":"csts-conditional-semantic-textual-similarity","title":"C-STS: Conditional Semantic Textual Similarity","date":"2023-05-24","arxiv_id":"2305.15093","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":4,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/csts-conditional-semantic-textual-similarity#ran","syntology_url":"https://syntology.ai/paper/2305.15093","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.15093"}},"official":{"repos":["princeton-nlp/c-sts"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/can-large-language-models-infer-and-disagree","slug":"can-large-language-models-infer-and-disagree","title":"Can Large Language Models Capture Dissenting Human Voices?","date":"2023-05-23","arxiv_id":"2305.13788","repositories_listed":1,"syntology":{"n":28,"n_ran":24,"n_constructed":0,"n_ran_checked":24,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":1,"n_no_contract":23,"n_pointer_only":0,"phrase":"24 ran (of which 0 constructed an object rather than computing a result; 24 with no instrument failure: 0 honoured, 1 violated, 23 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/can-large-language-models-infer-and-disagree#ran","syntology_url":"https://syntology.ai/paper/2305.13788","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.13788"}},"official":{"repos":["xfactlab/emnlp2023-llm-disagreement"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":14,"n_unverified":4,"ran_from_kinds":["found_in_text","official"]}}},{"url":"/paper/continual-dialogue-state-tracking-via-example","slug":"continual-dialogue-state-tracking-via-example","title":"Continual Dialogue State Tracking via Example-Guided Question Answering","date":"2023-05-23","arxiv_id":"2305.13721","repositories_listed":1,"syntology":null},{"url":"/paper/mpmr-a-multilingual-pre-trained-machine","slug":"mpmr-a-multilingual-pre-trained-machine","title":"mPMR: A Multilingual Pre-trained Machine Reader at Scale","date":"2023-05-23","arxiv_id":"2305.13645","repositories_listed":1,"syntology":null},{"url":"/paper/prompt-position-really-matters-in-few-shot","slug":"prompt-position-really-matters-in-few-shot","title":"Do prompt positions really matter?","date":"2023-05-23","arxiv_id":"2305.14493","repositories_listed":1,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":5,"n_pointer_only":7,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/prompt-position-really-matters-in-few-shot#ran","syntology_url":"https://syntology.ai/paper/2305.14493","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14493"}},"official":{"repos":["milliemaoo/prompt-position"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/question-answering-as-programming-for-solving","slug":"question-answering-as-programming-for-solving","title":"Question Answering as Programming for Solving Time-Sensitive Questions","date":"2023-05-23","arxiv_id":"2305.14221","repositories_listed":1,"syntology":null},{"url":"/paper/understanding-programs-by-exploiting-fuzzing","slug":"understanding-programs-by-exploiting-fuzzing","title":"Understanding Programs by Exploiting (Fuzzing) Test Cases","date":"2023-05-23","arxiv_id":"2305.13592","repositories_listed":1,"syntology":null},{"url":"/paper/wyweb-a-nlp-evaluation-benchmark-for","slug":"wyweb-a-nlp-evaluation-benchmark-for","title":"WYWEB: A NLP Evaluation Benchmark For Classical Chinese","date":"2023-05-23","arxiv_id":"2305.14150","repositories_listed":1,"syntology":null},{"url":"/paper/zeroscrolls-a-zero-shot-benchmark-for-long","slug":"zeroscrolls-a-zero-shot-benchmark-for-long","title":"ZeroSCROLLS: A Zero-Shot Benchmark for Long Text Understanding","date":"2023-05-23","arxiv_id":"2305.14196","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/zeroscrolls-a-zero-shot-benchmark-for-long#ran","syntology_url":"https://syntology.ai/paper/2305.14196","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14196"}},"official":{"repos":["tau-nlp/zero_scrolls"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/ambiguity-meets-uncertainty-investigating","slug":"ambiguity-meets-uncertainty-investigating","title":"Ambiguity Meets Uncertainty: Investigating Uncertainty Estimation for Word Sense Disambiguation","date":"2023-05-22","arxiv_id":"2305.13119","repositories_listed":1,"syntology":null},{"url":"/paper/logical-reasoning-for-natural-language","slug":"logical-reasoning-for-natural-language","title":"Atomic Inference for NLI with Generated Facts as Atoms","date":"2023-05-22","arxiv_id":"2305.13214","repositories_listed":1,"syntology":null},{"url":"/paper/zero-shot-end-to-end-spoken-language","slug":"zero-shot-end-to-end-spoken-language","title":"Zero-Shot End-to-End Spoken Language Understanding via Cross-Modal Selective Self-Training","date":"2023-05-22","arxiv_id":"2305.12793","repositories_listed":1,"syntology":null},{"url":"/paper/pruning-pre-trained-language-models-with","slug":"pruning-pre-trained-language-models-with","title":"Pruning Pre-trained Language Models with Principled Importance and Self-regularization","date":"2023-05-21","arxiv_id":"2305.12394","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/pruning-pre-trained-language-models-with#ran","syntology_url":"https://syntology.ai/paper/2305.12394","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.12394"}},"official":{"repos":["drsy/pins"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/tapir-learning-adaptive-revision-for","slug":"tapir-learning-adaptive-revision-for","title":"TAPIR: Learning Adaptive Revision for Incremental Natural Language Understanding with a Two-Pass Model","date":"2023-05-18","arxiv_id":"2305.10845","repositories_listed":1,"syntology":null},{"url":"/paper/berttm-leveraging-contextualized-word","slug":"berttm-leveraging-contextualized-word","title":"CWTM: Leveraging Contextualized Word Embeddings from BERT for Neural Topic Modeling","date":"2023-05-16","arxiv_id":"2305.09329","repositories_listed":1,"syntology":null},{"url":"/paper/make-prompt-based-black-box-tuning-colorful","slug":"make-prompt-based-black-box-tuning-colorful","title":"Make Prompt-based Black-Box Tuning Colorful: Boosting Model Generalization from Three Orthogonal Perspectives","date":"2023-05-14","arxiv_id":"2305.08088","repositories_listed":1,"syntology":null}],"record_sha256":"9561768515cdf58db02acf35e1cf93ad1fd45d4febd2915d1da7a7acd6ef4a25","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}