{"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":"/method/inverse-square-root-schedule/papers/4","list_of":"/method/inverse-square-root-schedule","method":"Inverse Square Root Schedule","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"date (newest first), then slug","page":4,"pages_in_order":8,"rows_per_page":100,"rows":[301,400],"of":702,"counts":{"archive_papers_tagged":702,"with_a_code_link":349,"where_syntology_ran_a_sample":97,"not_listed_spam_title":0,"listed":702,"listed_where_code_ran":97,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":83,"every_run_a_failure_of_syntologys_instrument":14,"listed_with_a_run_with_no_instrument_failure":83,"listed_every_run_a_failure_of_syntologys_instrument":14,"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":"/method/inverse-square-root-schedule","prev":"/method/inverse-square-root-schedule/papers/3","next":"/method/inverse-square-root-schedule/papers/5","papers":[{"paper":null,"slug":"deep-fusion-efficient-network-training-via","title":"Deep Fusion: Efficient Network Training via Pre-trained Initializations","date":"2023-06-20","arxiv_id":"2306.11903","n_code_links":0,"syntology":null},{"paper":"/paper/fine-tuning-language-models-for-scientific","slug":"fine-tuning-language-models-for-scientific","title":"Fine-Tuning Language Models for Scientific Writing Support","date":"2023-06-19","arxiv_id":"2306.10974","n_code_links":1,"syntology":null},{"paper":null,"slug":"summarization-from-leaderboards-to-practice","title":"Summarization from Leaderboards to Practice: Choosing A Representation Backbone and Ensuring Robustness","date":"2023-06-18","arxiv_id":"2306.10555","n_code_links":0,"syntology":null},{"paper":"/paper/unipoll-a-unified-social-media-poll","slug":"unipoll-a-unified-social-media-poll","title":"UniPoll: A Unified Social Media Poll Generation Framework via Multi-Objective Optimization","date":"2023-06-12","arxiv_id":"2306.06851","n_code_links":1,"syntology":null},{"paper":"/paper/attention-compilation-and-solver-based","slug":"attention-compilation-and-solver-based","title":"CoTran: An LLM-based Code Translator using Reinforcement Learning with Feedback from Compiler and Symbolic Execution","date":"2023-06-11","arxiv_id":"2306.06755","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-unified-generative-approach-to-product","title":"A Unified Generative Approach to Product Attribute-Value Identification","date":"2023-06-09","arxiv_id":"2306.05605","n_code_links":0,"syntology":null},{"paper":null,"slug":"triggering-multi-hop-reasoning-for-question","title":"Triggering Multi-Hop Reasoning for Question Answering in Language Models using Soft Prompts and Random Walks","date":"2023-06-06","arxiv_id":"2306.04009","n_code_links":0,"syntology":null},{"paper":"/paper/detector-guidance-for-multi-object-text-to","slug":"detector-guidance-for-multi-object-text-to","title":"Detector Guidance for Multi-Object Text-to-Image Generation","date":"2023-06-04","arxiv_id":"2306.02236","n_code_links":1,"syntology":null},{"paper":null,"slug":"modular-transformers-compressing-transformers","title":"Modular Transformers: Compressing Transformers into Modularized Layers for Flexible Efficient Inference","date":"2023-06-04","arxiv_id":"2306.02379","n_code_links":0,"syntology":null},{"paper":null,"slug":"5ider-unified-query-rewriting-for-steering","title":"5IDER: Unified Query Rewriting for Steering, Intent Carryover, Disfluencies, Entity Carryover and Repair","date":"2023-06-02","arxiv_id":"2306.01855","n_code_links":0,"syntology":null},{"paper":"/paper/adapting-pre-trained-language-models-to","slug":"adapting-pre-trained-language-models-to","title":"Adapting Pre-trained Language Models to Vision-Language Tasks via Dynamic Visual Prompting","date":"2023-06-01","arxiv_id":"2306.00409","n_code_links":1,"syntology":null},{"paper":null,"slug":"prequant-a-task-agnostic-quantization","title":"PreQuant: A Task-agnostic Quantization Approach for Pre-trained Language Models","date":"2023-05-30","arxiv_id":"2306.00014","n_code_links":0,"syntology":null},{"paper":null,"slug":"coeditor-leveraging-contextual-changes-for","title":"Coeditor: Leveraging Contextual Changes for Multi-round Code Auto-editing","date":"2023-05-29","arxiv_id":"2305.18584","n_code_links":0,"syntology":null},{"paper":"/paper/how-effective-are-neural-networks-for-fixing","slug":"how-effective-are-neural-networks-for-fixing","title":"How Effective Are Neural Networks for Fixing Security Vulnerabilities","date":"2023-05-29","arxiv_id":"2305.18607","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":0,"n_instrument":4,"unverified":0,"pointer_only":4,"phrase":"4 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; 4 where Syntology's instrument failed) · 0 unverified","official":{"repos":["lin-tan/llm-vul"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/knowledge-augmented-reasoning-distillation-1","slug":"knowledge-augmented-reasoning-distillation-1","title":"Knowledge-Augmented Reasoning Distillation for Small Language Models in Knowledge-Intensive Tasks","date":"2023-05-28","arxiv_id":"2305.18395","n_code_links":1,"syntology":{"ran":5,"of":6,"n_ran_checked":3,"n_instrument":2,"unverified":1,"pointer_only":1,"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) · 1 unverified","official":{"repos":["nardien/kard"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/towards-explainable-conversational","slug":"towards-explainable-conversational","title":"Towards Explainable Conversational Recommender Systems","date":"2023-05-27","arxiv_id":"2305.18363","n_code_links":1,"syntology":null},{"paper":"/paper/beyond-chain-of-thought-effective-graph-of","slug":"beyond-chain-of-thought-effective-graph-of","title":"Beyond Chain-of-Thought, Effective Graph-of-Thought Reasoning in Language Models","date":"2023-05-26","arxiv_id":"2305.16582","n_code_links":2,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":2,"phrase":"2 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; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["zoeyyao27/graph-of-thought"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/learning-to-imagine-visually-augmented","slug":"learning-to-imagine-visually-augmented","title":"Learning to Imagine: Visually-Augmented Natural Language Generation","date":"2023-05-26","arxiv_id":"2305.16944","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"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","official":{"repos":["rucaibox/live"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text"]}}},{"paper":"/paper/pre-training-meets-clustering-a-hybrid","slug":"pre-training-meets-clustering-a-hybrid","title":"Pre-training Meets Clustering: A Hybrid Extractive Multi-document Summarization Model","date":"2023-05-25","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"neural-summarization-of-electronic-health","title":"Neural Summarization of Electronic Health Records","date":"2023-05-24","arxiv_id":"2305.15222","n_code_links":0,"syntology":null},{"paper":"/paper/exploring-large-language-models-for-classical","slug":"exploring-large-language-models-for-classical","title":"Exploring Large Language Models for Classical Philology","date":"2023-05-23","arxiv_id":"2305.13698","n_code_links":1,"syntology":null},{"paper":null,"slug":"grace-generation-using-associated-code-edits","title":"GrACE: Generation using Associated Code Edits","date":"2023-05-23","arxiv_id":"2305.14129","n_code_links":0,"syntology":null},{"paper":null,"slug":"mmt5-modular-multilingual-pre-training-solves","title":"mmT5: Modular Multilingual Pre-Training Solves Source Language Hallucinations","date":"2023-05-23","arxiv_id":"2305.14224","n_code_links":0,"syntology":null},{"paper":null,"slug":"nail-lexical-retrieval-indices-with-efficient","title":"NAIL: Lexical Retrieval Indices with Efficient Non-Autoregressive Decoders","date":"2023-05-23","arxiv_id":"2305.14499","n_code_links":0,"syntology":null},{"paper":"/paper/on-robustness-of-finetuned-transformer-based","slug":"on-robustness-of-finetuned-transformer-based","title":"On Robustness of Finetuned Transformer-based NLP Models","date":"2023-05-23","arxiv_id":"2305.14453","n_code_links":1,"syntology":null},{"paper":"/paper/towards-massively-multi-domain-multilingual","slug":"towards-massively-multi-domain-multilingual","title":"ReadMe++: Benchmarking Multilingual Language Models for Multi-Domain Readability Assessment","date":"2023-05-23","arxiv_id":"2305.14463","n_code_links":1,"syntology":null},{"paper":"/paper/sparsefit-few-shot-prompting-with-sparse-fine","slug":"sparsefit-few-shot-prompting-with-sparse-fine","title":"SPARSEFIT: Few-shot Prompting with Sparse Fine-tuning for Jointly Generating Predictions and Natural Language Explanations","date":"2023-05-22","arxiv_id":"2305.13235","n_code_links":1,"syntology":null},{"paper":"/paper/model-generated-pretraining-signals-improves","slug":"model-generated-pretraining-signals-improves","title":"Model-Generated Pretraining Signals Improves Zero-Shot Generalization of Text-to-Text Transformers","date":"2023-05-21","arxiv_id":"2305.12567","n_code_links":1,"syntology":null},{"paper":null,"slug":"can-nlp-models-correctly-reason-over-contexts","title":"Can NLP Models Correctly Reason Over Contexts that Break the Common Assumptions?","date":"2023-05-20","arxiv_id":"2305.12096","n_code_links":0,"syntology":null},{"paper":null,"slug":"do-models-really-learn-to-follow-instructions","title":"Do Models Really Learn to Follow Instructions? An Empirical Study of Instruction Tuning","date":"2023-05-19","arxiv_id":"2305.11383","n_code_links":0,"syntology":null},{"paper":null,"slug":"generalized-multiple-intent-conditioned-slot","title":"Generalized Multiple Intent Conditioned Slot Filling","date":"2023-05-18","arxiv_id":"2305.11023","n_code_links":0,"syntology":null},{"paper":"/paper/mlongt5-a-multilingual-and-efficient-text-to","slug":"mlongt5-a-multilingual-and-efficient-text-to","title":"mLongT5: A Multilingual and Efficient Text-To-Text Transformer for Longer Sequences","date":"2023-05-18","arxiv_id":"2305.11129","n_code_links":1,"syntology":null},{"paper":"/paper/instruction-tuned-models-are-quick-learners","slug":"instruction-tuned-models-are-quick-learners","title":"Instruction Tuned Models are Quick Learners","date":"2023-05-17","arxiv_id":"2306.05539","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 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; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["srsawant34/efficient_instruction_learning"],"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"]}}},{"paper":"/paper/document-understanding-dataset-and-evaluation","slug":"document-understanding-dataset-and-evaluation","title":"Document Understanding Dataset and Evaluation (DUDE)","date":"2023-05-15","arxiv_id":"2305.08455","n_code_links":1,"syntology":{"ran":4,"of":5,"n_ran_checked":4,"n_instrument":0,"unverified":1,"pointer_only":0,"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) · 1 unverified","official":{"repos":["rubenpt91/MP-DocVQA-Framework"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"sensitivity-and-robustness-of-large-language","title":"Sensitivity and Robustness of Large Language Models to Prompt Template in Japanese Text Classification Tasks","date":"2023-05-15","arxiv_id":"2305.08714","n_code_links":0,"syntology":null},{"paper":"/paper/nl2tl-transforming-natural-languages-to","slug":"nl2tl-transforming-natural-languages-to","title":"NL2TL: Transforming Natural Languages to Temporal Logics using Large Language Models","date":"2023-05-12","arxiv_id":"2305.07766","n_code_links":3,"syntology":{"ran":5,"of":9,"n_ran_checked":2,"n_instrument":3,"unverified":4,"pointer_only":8,"phrase":"5 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; 3 where Syntology's instrument failed) · 4 unverified","official":{"repos":["yongchao98/nl2tl"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official","unlocated"]}}},{"paper":null,"slug":"rnns-representation-nearest-neighbor-search","title":"A Black-Box Attack on Code Models via Representation Nearest Neighbor Search","date":"2023-05-10","arxiv_id":"2305.05896","n_code_links":0,"syntology":null},{"paper":"/paper/an-exploration-of-encoder-decoder-approaches","slug":"an-exploration-of-encoder-decoder-approaches","title":"An Exploration of Encoder-Decoder Approaches to Multi-Label Classification for Legal and Biomedical Text","date":"2023-05-09","arxiv_id":"2305.05627","n_code_links":1,"syntology":null},{"paper":null,"slug":"multi-task-end-to-end-training-improves-1","title":"Multi-Task End-to-End Training Improves Conversational Recommendation","date":"2023-05-08","arxiv_id":"2305.06218","n_code_links":0,"syntology":null},{"paper":"/paper/distilling-step-by-step-outperforming-larger","slug":"distilling-step-by-step-outperforming-larger","title":"Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes","date":"2023-05-03","arxiv_id":"2305.02301","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":4,"n_instrument":0,"unverified":0,"pointer_only":0,"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","official":{"repos":["google-research/distilling-step-by-step"],"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"]}}},{"paper":"/paper/entity-tracking-in-language-models","slug":"entity-tracking-in-language-models","title":"Entity Tracking in Language Models","date":"2023-05-03","arxiv_id":"2305.02363","n_code_links":1,"syntology":null},{"paper":null,"slug":"neural-keyphrase-generation-analysis-and-1","title":"Neural Keyphrase Generation: Analysis and Evaluation","date":"2023-04-27","arxiv_id":"2304.13883","n_code_links":0,"syntology":null},{"paper":"/paper/introducing-mbib-the-first-media-bias","slug":"introducing-mbib-the-first-media-bias","title":"Introducing MBIB -- the first Media Bias Identification Benchmark Task and Dataset Collection","date":"2023-04-25","arxiv_id":"2304.13148","n_code_links":1,"syntology":null},{"paper":"/paper/text-to-audio-generation-using-instruction","slug":"text-to-audio-generation-using-instruction","title":"Text-to-Audio Generation using Instruction-Tuned LLM and Latent Diffusion Model","date":"2023-04-24","arxiv_id":"2304.13731","n_code_links":1,"syntology":null},{"paper":"/paper/longform-optimizing-instruction-tuning-for","slug":"longform-optimizing-instruction-tuning-for","title":"LongForm: Effective Instruction Tuning with Reverse Instructions","date":"2023-04-17","arxiv_id":"2304.08460","n_code_links":2,"syntology":null},{"paper":"/paper/the-minipile-challenge-for-data-efficient","slug":"the-minipile-challenge-for-data-efficient","title":"The MiniPile Challenge for Data-Efficient Language Models","date":"2023-04-17","arxiv_id":"2304.08442","n_code_links":1,"syntology":null},{"paper":null,"slug":"automated-program-repair-based-on-code-review","title":"Enhancing Automated Program Repair through Fine-tuning and Prompt Engineering","date":"2023-04-16","arxiv_id":"2304.07840","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-the-use-of-foundation-models-for","title":"Exploring the Use of Foundation Models for Named Entity Recognition and Lemmatization Tasks in Slavic Languages","date":"2023-04-11","arxiv_id":"2304.05336","n_code_links":0,"syntology":null},{"paper":"/paper/chartreader-a-unified-framework-for-chart","slug":"chartreader-a-unified-framework-for-chart","title":"ChartReader: A Unified Framework for Chart Derendering and Comprehension without Heuristic Rules","date":"2023-04-05","arxiv_id":"2304.02173","n_code_links":1,"syntology":{"ran":16,"of":19,"n_ran_checked":6,"n_instrument":10,"unverified":3,"pointer_only":19,"phrase":"16 ran (of which 3 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 10 where Syntology's instrument failed) · 3 unverified","official":{"repos":["zhiqic/chartreader"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":3,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/generating-natural-language-from-logic","slug":"generating-natural-language-from-logic","title":"Generating Natural Language from Logic Expressions with Structural Representation","date":"2023-04-04","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/peach-pre-training-sequence-to-sequence","slug":"peach-pre-training-sequence-to-sequence","title":"PEACH: Pre-Training Sequence-to-Sequence Multilingual Models for Translation with Semi-Supervised Pseudo-Parallel Document Generation","date":"2023-04-03","arxiv_id":"2304.01282","n_code_links":1,"syntology":null},{"paper":"/paper/the-statcan-dialogue-dataset-retrieving-data","slug":"the-statcan-dialogue-dataset-retrieving-data","title":"The StatCan Dialogue Dataset: Retrieving Data Tables through Conversations with Genuine Intents","date":"2023-04-03","arxiv_id":"2304.01412","n_code_links":1,"syntology":null},{"paper":"/paper/understanding-individual-and-team-based-human","slug":"understanding-individual-and-team-based-human","title":"Does Human Collaboration Enhance the Accuracy of Identifying LLM-Generated Deepfake Texts?","date":"2023-04-03","arxiv_id":"2304.01002","n_code_links":2,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":0,"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) · 0 unverified","official":{"repos":["huashen218/llm-deepfake-human-study"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/better-language-models-of-code-through-self","slug":"better-language-models-of-code-through-self","title":"Better Language Models of Code through Self-Improvement","date":"2023-04-02","arxiv_id":"2304.01228","n_code_links":1,"syntology":null},{"paper":null,"slug":"synthesis-of-mathematical-programs-from","title":"Synthesis of Mathematical programs from Natural Language Specifications","date":"2023-03-30","arxiv_id":"2304.03287","n_code_links":0,"syntology":null},{"paper":null,"slug":"summarizing-indian-languages-using","title":"Summarizing Indian Languages using Multilingual Transformers based Models","date":"2023-03-29","arxiv_id":"2303.16657","n_code_links":0,"syntology":null},{"paper":"/paper/explicit-planning-helps-language-models-in","slug":"explicit-planning-helps-language-models-in","title":"Explicit Planning Helps Language Models in Logical Reasoning","date":"2023-03-28","arxiv_id":"2303.15714","n_code_links":2,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"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","official":{"repos":["cindermond/explicit-planning-for-reasoning","cindermond/leap"],"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"]}}},{"paper":"/paper/neuralmind-unicamp-at-2022-trec-neuclir-large","slug":"neuralmind-unicamp-at-2022-trec-neuclir-large","title":"NeuralMind-UNICAMP at 2022 TREC NeuCLIR: Large Boring Rerankers for Cross-lingual Retrieval","date":"2023-03-28","arxiv_id":"2303.16145","n_code_links":1,"syntology":null},{"paper":"/paper/one-adapter-for-all-programming-languages","slug":"one-adapter-for-all-programming-languages","title":"One Adapter for All Programming Languages? Adapter Tuning for Code Search and Summarization","date":"2023-03-28","arxiv_id":"2303.15822","n_code_links":1,"syntology":null},{"paper":null,"slug":"automatic-generation-of-multiple-choice","title":"Automatic Generation of Multiple-Choice Questions","date":"2023-03-25","arxiv_id":"2303.14576","n_code_links":0,"syntology":null},{"paper":"/paper/dblp-quad-a-question-answering-dataset-over","slug":"dblp-quad-a-question-answering-dataset-over","title":"DBLP-QuAD: A Question Answering Dataset over the DBLP Scholarly Knowledge Graph","date":"2023-03-23","arxiv_id":"2303.13351","n_code_links":1,"syntology":null},{"paper":"/paper/gett-qa-graph-embedding-based-t2t-transformer","slug":"gett-qa-graph-embedding-based-t2t-transformer","title":"GETT-QA: Graph Embedding based T2T Transformer for Knowledge Graph Question Answering","date":"2023-03-23","arxiv_id":"2303.13284","n_code_links":1,"syntology":null},{"paper":"/paper/open-source-frame-semantic-parsing","slug":"open-source-frame-semantic-parsing","title":"Open-source Frame Semantic Parsing","date":"2023-03-22","arxiv_id":"2303.12788","n_code_links":1,"syntology":null},{"paper":"/paper/bangla-grammatical-error-detection-using-t5","slug":"bangla-grammatical-error-detection-using-t5","title":"Bangla Grammatical Error Detection Using T5 Transformer Model","date":"2023-03-19","arxiv_id":"2303.10612","n_code_links":2,"syntology":null},{"paper":null,"slug":"exploring-distributional-shifts-in-large","title":"Exploring Distributional Shifts in Large Language Models for Code Analysis","date":"2023-03-16","arxiv_id":"2303.09128","n_code_links":0,"syntology":null},{"paper":"/paper/typet5-seq2seq-type-inference-using-static","slug":"typet5-seq2seq-type-inference-using-static","title":"TypeT5: Seq2seq Type Inference using Static Analysis","date":"2023-03-16","arxiv_id":"2303.09564","n_code_links":1,"syntology":{"ran":4,"of":7,"n_ran_checked":4,"n_instrument":0,"unverified":3,"pointer_only":0,"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) · 3 unverified","official":{"repos":["utopia-group/typet5"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/presto-a-multilingual-dataset-for-parsing","slug":"presto-a-multilingual-dataset-for-parsing","title":"PRESTO: A Multilingual Dataset for Parsing Realistic Task-Oriented Dialogs","date":"2023-03-15","arxiv_id":"2303.08954","n_code_links":1,"syntology":null},{"paper":"/paper/proactive-prioritization-of-app-issues-via","slug":"proactive-prioritization-of-app-issues-via","title":"Proactive Prioritization of App Issues via Contrastive Learning","date":"2023-03-12","arxiv_id":"2303.06586","n_code_links":1,"syntology":null},{"paper":"/paper/a-comprehensive-survey-of-ai-generated","slug":"a-comprehensive-survey-of-ai-generated","title":"A Comprehensive Survey of AI-Generated Content (AIGC): A History of Generative AI from GAN to ChatGPT","date":"2023-03-07","arxiv_id":"2303.04226","n_code_links":1,"syntology":null},{"paper":null,"slug":"spelling-convention-sensitivity-in-neural","title":"Spelling convention sensitivity in neural language models","date":"2023-03-06","arxiv_id":"2303.03457","n_code_links":0,"syntology":null},{"paper":null,"slug":"n-best-t5-robust-asr-error-correction-using","title":"N-best T5: Robust ASR Error Correction using Multiple Input Hypotheses and Constrained Decoding Space","date":"2023-03-01","arxiv_id":"2303.00456","n_code_links":0,"syntology":null},{"paper":"/paper/are-character-level-translations-worth-the","slug":"are-character-level-translations-worth-the","title":"Are Character-level Translations Worth the Wait? Comparing ByT5 and mT5 for Machine Translation","date":"2023-02-28","arxiv_id":"2302.14220","n_code_links":1,"syntology":null},{"paper":"/paper/choice-fusion-as-knowledge-for-zero-shot","slug":"choice-fusion-as-knowledge-for-zero-shot","title":"Choice Fusion as Knowledge for Zero-Shot Dialogue State Tracking","date":"2023-02-25","arxiv_id":"2302.13013","n_code_links":1,"syntology":null},{"paper":"/paper/prompt-based-learning-for-text-readability","slug":"prompt-based-learning-for-text-readability","title":"Prompt-based Learning for Text Readability Assessment","date":"2023-02-25","arxiv_id":"2302.13139","n_code_links":1,"syntology":null},{"paper":"/paper/does-deep-learning-learn-to-abstract-a","slug":"does-deep-learning-learn-to-abstract-a","title":"Does Deep Learning Learn to Abstract? A Systematic Probing Framework","date":"2023-02-23","arxiv_id":"2302.11978","n_code_links":1,"syntology":null},{"paper":"/paper/vlsp-2022-evjvqa-challenge-multilingual","slug":"vlsp-2022-evjvqa-challenge-multilingual","title":"EVJVQA Challenge: Multilingual Visual Question Answering","date":"2023-02-23","arxiv_id":"2302.11752","n_code_links":0,"syntology":null},{"paper":"/paper/bbt-fin-comprehensive-construction-of-chinese","slug":"bbt-fin-comprehensive-construction-of-chinese","title":"BBT-Fin: Comprehensive Construction of Chinese Financial Domain Pre-trained Language Model, Corpus and Benchmark","date":"2023-02-18","arxiv_id":"2302.09432","n_code_links":2,"syntology":null},{"paper":"/paper/pac-prediction-sets-for-large-language-models","slug":"pac-prediction-sets-for-large-language-models","title":"PAC Prediction Sets for Large Language Models of Code","date":"2023-02-17","arxiv_id":"2302.08703","n_code_links":1,"syntology":null},{"paper":null,"slug":"commonsense-reasoning-for-conversational-ai-a","title":"Commonsense Reasoning for Conversational AI: A Survey of the State of the Art","date":"2023-02-15","arxiv_id":"2302.07926","n_code_links":0,"syntology":null},{"paper":null,"slug":"few-shot-learning-approaches-for-classifying","title":"Few-shot learning approaches for classifying low resource domain specific software requirements","date":"2023-02-14","arxiv_id":"2302.06951","n_code_links":0,"syntology":null},{"paper":null,"slug":"linguistic-ambiguity-analysis-in-chatgpt","title":"Linguistic ambiguity analysis in ChatGPT","date":"2023-02-13","arxiv_id":"2302.06426","n_code_links":0,"syntology":null},{"paper":null,"slug":"street-a-multi-task-structured-reasoning-and","title":"STREET: A Multi-Task Structured Reasoning and Explanation Benchmark","date":"2023-02-13","arxiv_id":"2302.06729","n_code_links":0,"syntology":null},{"paper":"/paper/controllable-lexical-simplification-for","slug":"controllable-lexical-simplification-for","title":"Controllable Lexical Simplification for English","date":"2023-02-06","arxiv_id":"2302.02900","n_code_links":1,"syntology":null},{"paper":null,"slug":"idt5-indonesian-version-of-multilingual-t5","title":"idT5: Indonesian Version of Multilingual T5 Transformer","date":"2023-02-02","arxiv_id":"2302.00856","n_code_links":0,"syntology":null},{"paper":"/paper/hunsum-1-an-abstractive-summarization-dataset","slug":"hunsum-1-an-abstractive-summarization-dataset","title":"HunSum-1: an Abstractive Summarization Dataset for Hungarian","date":"2023-02-01","arxiv_id":"2302.00455","n_code_links":1,"syntology":null},{"paper":null,"slug":"flame-a-small-language-model-for-spreadsheet","title":"FLAME: A small language model for spreadsheet formulas","date":"2023-01-31","arxiv_id":"2301.13779","n_code_links":0,"syntology":null},{"paper":"/paper/the-flan-collection-designing-data-and","slug":"the-flan-collection-designing-data-and","title":"The Flan Collection: Designing Data and Methods for Effective Instruction Tuning","date":"2023-01-31","arxiv_id":"2301.13688","n_code_links":1,"syntology":null},{"paper":"/paper/specializing-smaller-language-models-towards","slug":"specializing-smaller-language-models-towards","title":"Specializing Smaller Language Models towards Multi-Step Reasoning","date":"2023-01-30","arxiv_id":"2301.12726","n_code_links":2,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"2 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; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["FranxYao/FlanT5-CoT-Specialization"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/progressive-prompts-continual-learning-for","slug":"progressive-prompts-continual-learning-for","title":"Progressive Prompts: Continual Learning for Language Models","date":"2023-01-29","arxiv_id":"2301.12314","n_code_links":2,"syntology":{"ran":8,"of":11,"n_ran_checked":8,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["arazd/ProgressivePrompts"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/schema-guided-semantic-accuracy-faithfulness","slug":"schema-guided-semantic-accuracy-faithfulness","title":"Schema-Guided Semantic Accuracy: Faithfulness in Task-Oriented Dialogue Response Generation","date":"2023-01-29","arxiv_id":"2301.12568","n_code_links":1,"syntology":null},{"paper":"/paper/bipol-multi-axes-evaluation-of-bias-with","slug":"bipol-multi-axes-evaluation-of-bias-with","title":"Bipol: Multi-axes Evaluation of Bias with Explainability in Benchmark Datasets","date":"2023-01-28","arxiv_id":"2301.12139","n_code_links":2,"syntology":null},{"paper":null,"slug":"a-stability-analysis-of-fine-tuning-a-pre","title":"A Stability Analysis of Fine-Tuning a Pre-Trained Model","date":"2023-01-24","arxiv_id":"2301.09820","n_code_links":0,"syntology":null},{"paper":null,"slug":"multitask-instruction-based-prompting-for","title":"Multitask Instruction-based Prompting for Fallacy Recognition","date":"2023-01-24","arxiv_id":"2301.09992","n_code_links":0,"syntology":null},{"paper":"/paper/graphix-t5-mixing-pre-trained-transformers","slug":"graphix-t5-mixing-pre-trained-transformers","title":"Graphix-T5: Mixing Pre-Trained Transformers with Graph-Aware Layers for Text-to-SQL Parsing","date":"2023-01-18","arxiv_id":"2301.07507","n_code_links":1,"syntology":null},{"paper":"/paper/there-is-no-big-brother-or-small-brother","slug":"there-is-no-big-brother-or-small-brother","title":"There is No Big Brother or Small Brother: Knowledge Infusion in Language Models for Link Prediction and Question Answering","date":"2023-01-10","arxiv_id":"2301.04013","n_code_links":2,"syntology":null},{"paper":null,"slug":"conditional-generation-of-paired-antibody","title":"Generative Antibody Design for Complementary Chain Pairing Sequences through Encoder-Decoder Language Model","date":"2023-01-06","arxiv_id":"2301.02748","n_code_links":0,"syntology":null},{"paper":"/paper/extending-source-code-pre-trained-language","slug":"extending-source-code-pre-trained-language","title":"Extending Source Code Pre-Trained Language Models to Summarise Decompiled Binaries","date":"2023-01-04","arxiv_id":"2301.01701","n_code_links":1,"syntology":null},{"paper":null,"slug":"transformer-based-geocoding","title":"Transformer Based Geocoding","date":"2023-01-02","arxiv_id":"2301.01170","n_code_links":0,"syntology":null},{"paper":"/paper/on-the-inconsistencies-of-conditionals","slug":"on-the-inconsistencies-of-conditionals","title":"Inconsistencies in Masked Language Models","date":"2022-12-30","arxiv_id":"2301.00068","n_code_links":1,"syntology":null},{"paper":null,"slug":"error-syntax-aware-augmentation-of-feedback","title":"Error syntax aware augmentation of feedback comment generation dataset","date":"2022-12-29","arxiv_id":"2212.14293","n_code_links":0,"syntology":null}],"record_sha256":"f01a53042be3253d32c875eeb7b6b442d4572edba3a06d514496dacf0253a15f","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}