{"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/gpt-2/papers/5","list_of":"/method/gpt-2","method":"GPT-2","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":5,"pages_in_order":8,"rows_per_page":100,"rows":[401,500],"of":768,"counts":{"archive_papers_tagged":768,"with_a_code_link":339,"where_syntology_ran_a_sample":125,"not_listed_spam_title":0,"listed":768,"listed_where_code_ran":125,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":99,"every_run_a_failure_of_syntologys_instrument":26,"listed_with_a_run_with_no_instrument_failure":99,"listed_every_run_a_failure_of_syntologys_instrument":26,"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/gpt-2","prev":"/method/gpt-2/papers/4","next":"/method/gpt-2/papers/6","papers":[{"paper":"/paper/semantic-coherence-markers-for-the-early","slug":"semantic-coherence-markers-for-the-early","title":"Semantic Coherence Markers for the Early Diagnosis of the Alzheimer Disease","date":"2023-02-02","arxiv_id":"2302.01025","n_code_links":1,"syntology":null},{"paper":"/paper/analyzing-leakage-of-personally-identifiable","slug":"analyzing-leakage-of-personally-identifiable","title":"Analyzing Leakage of Personally Identifiable Information in Language Models","date":"2023-02-01","arxiv_id":"2302.00539","n_code_links":1,"syntology":null},{"paper":null,"slug":"incorporating-knowledge-into-document","title":"The Exploration of Knowledge-Preserving Prompts for Document Summarisation","date":"2023-01-27","arxiv_id":"2301.11719","n_code_links":0,"syntology":null},{"paper":"/paper/audience-centric-natural-language-generation","slug":"audience-centric-natural-language-generation","title":"Audience-Centric Natural Language Generation via Style Infusion","date":"2023-01-24","arxiv_id":"2301.10283","n_code_links":1,"syntology":null},{"paper":null,"slug":"automatic-generation-of-german-drama-texts","title":"Automatic Generation of German Drama Texts Using Fine Tuned GPT-2 Models","date":"2023-01-08","arxiv_id":"2301.03119","n_code_links":0,"syntology":null},{"paper":null,"slug":"sequentially-controlled-text-generation-1","title":"Sequentially Controlled Text Generation","date":"2023-01-05","arxiv_id":"2301.02299","n_code_links":0,"syntology":null},{"paper":null,"slug":"targeted-phishing-campaigns-using-large-scale","title":"Targeted Phishing Campaigns using Large Scale Language Models","date":"2022-12-30","arxiv_id":"2301.00665","n_code_links":0,"syntology":null},{"paper":null,"slug":"tegformer-topic-to-essay-generation-with-good","title":"TegFormer: Topic-to-Essay Generation with Good Topic Coverage and High Text Coherence","date":"2022-12-27","arxiv_id":"2212.13456","n_code_links":0,"syntology":null},{"paper":null,"slug":"why-does-surprisal-from-larger-transformer","title":"Why Does Surprisal From Larger Transformer-Based Language Models Provide a Poorer Fit to Human Reading Times?","date":"2022-12-23","arxiv_id":"2212.12131","n_code_links":0,"syntology":null},{"paper":"/paper/entropy-and-distance-based-predictors-from","slug":"entropy-and-distance-based-predictors-from","title":"Entropy- and Distance-Based Predictors From GPT-2 Attention Patterns Predict Reading Times Over and Above GPT-2 Surprisal","date":"2022-12-21","arxiv_id":"2212.11185","n_code_links":1,"syntology":{"ran":7,"of":11,"n_ran_checked":7,"n_instrument":0,"unverified":4,"pointer_only":8,"phrase":"7 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; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["byungdoh/attn_dist"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/bygpt5-end-to-end-style-conditioned-poetry","slug":"bygpt5-end-to-end-style-conditioned-poetry","title":"ByGPT5: End-to-End Style-conditioned Poetry Generation with Token-free Language Models","date":"2022-12-20","arxiv_id":"2212.10474","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"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) · 0 unverified","official":{"repos":["potamides/uniformers"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/the-case-for-4-bit-precision-k-bit-inference","slug":"the-case-for-4-bit-precision-k-bit-inference","title":"The case for 4-bit precision: k-bit Inference Scaling Laws","date":"2022-12-19","arxiv_id":"2212.09720","n_code_links":1,"syntology":null},{"paper":null,"slug":"murmur-modular-multi-step-reasoning-for-semi","title":"MURMUR: Modular Multi-Step Reasoning for Semi-Structured Data-to-Text Generation","date":"2022-12-16","arxiv_id":"2212.08607","n_code_links":0,"syntology":null},{"paper":"/paper/elixir-train-a-large-language-model-on-a","slug":"elixir-train-a-large-language-model-on-a","title":"Elixir: Train a Large Language Model on a Small GPU Cluster","date":"2022-12-10","arxiv_id":"2212.05339","n_code_links":2,"syntology":null},{"paper":null,"slug":"the-turing-deception","title":"The Turing Deception","date":"2022-12-09","arxiv_id":"2212.06721","n_code_links":0,"syntology":null},{"paper":null,"slug":"trbllmaker-transformer-reads-between-lyrics","title":"TRBLLmaker -- Transformer Reads Between Lyrics Lines maker","date":"2022-12-09","arxiv_id":"2212.04917","n_code_links":0,"syntology":null},{"paper":"/paper/explain-to-me-like-i-am-five-sentence","slug":"explain-to-me-like-i-am-five-sentence","title":"Explain to me like I am five -- Sentence Simplification Using Transformers","date":"2022-12-08","arxiv_id":"2212.04595","n_code_links":1,"syntology":null},{"paper":null,"slug":"modern-french-poetry-generation-with-roberta","title":"Modern French Poetry Generation with RoBERTa and GPT-2","date":"2022-12-06","arxiv_id":"2212.02911","n_code_links":0,"syntology":null},{"paper":null,"slug":"automatic-generation-of-factual-news","title":"Automatic Generation of Factual News Headlines in Finnish","date":"2022-12-05","arxiv_id":"2212.02170","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-the-limits-of-differentially","title":"Exploring the Limits of Differentially Private Deep Learning with Group-wise Clipping","date":"2022-12-03","arxiv_id":"2212.01539","n_code_links":0,"syntology":null},{"paper":"/paper/distilling-multi-step-reasoning-capabilities","slug":"distilling-multi-step-reasoning-capabilities","title":"Distilling Reasoning Capabilities into Smaller Language Models","date":"2022-12-01","arxiv_id":"2212.00193","n_code_links":1,"syntology":null},{"paper":null,"slug":"quadapter-adapter-for-gpt-2-quantization","title":"Quadapter: Adapter for GPT-2 Quantization","date":"2022-11-30","arxiv_id":"2211.16912","n_code_links":0,"syntology":null},{"paper":"/paper/gpt-neo-for-commonsense-reasoning-a","slug":"gpt-neo-for-commonsense-reasoning-a","title":"GPT-Neo for commonsense reasoning -- a theoretical and practical lens","date":"2022-11-28","arxiv_id":"2211.15593","n_code_links":1,"syntology":null},{"paper":"/paper/scientific-and-creative-analogies-in","slug":"scientific-and-creative-analogies-in","title":"Scientific and Creative Analogies in Pretrained Language Models","date":"2022-11-28","arxiv_id":"2211.15268","n_code_links":2,"syntology":null},{"paper":null,"slug":"understanding-bloom-an-empirical-study-on","title":"Understanding BLOOM: An empirical study on diverse NLP tasks","date":"2022-11-27","arxiv_id":"2211.14865","n_code_links":0,"syntology":null},{"paper":"/paper/exploring-the-efficacy-of-pre-trained","slug":"exploring-the-efficacy-of-pre-trained","title":"Exploring the Efficacy of Pre-trained Checkpoints in Text-to-Music Generation Task","date":"2022-11-21","arxiv_id":"2211.11216","n_code_links":2,"syntology":null},{"paper":null,"slug":"a-survey-on-knowledge-enhanced-multimodal","title":"A survey on knowledge-enhanced multimodal learning","date":"2022-11-19","arxiv_id":"2211.12328","n_code_links":0,"syntology":null},{"paper":null,"slug":"tsmind-alibaba-and-soochow-university-s","title":"TSMind: Alibaba and Soochow University's Submission to the WMT22 Translation Suggestion Task","date":"2022-11-16","arxiv_id":"2211.08987","n_code_links":0,"syntology":null},{"paper":null,"slug":"textual-data-augmentation-for-patient","title":"Textual Data Augmentation for Patient Outcomes Prediction","date":"2022-11-13","arxiv_id":"2211.06778","n_code_links":0,"syntology":null},{"paper":"/paper/what-would-harry-say-building-dialogue-agents","slug":"what-would-harry-say-building-dialogue-agents","title":"Large Language Models Meet Harry Potter: A Bilingual Dataset for Aligning Dialogue Agents with Characters","date":"2022-11-13","arxiv_id":"2211.06869","n_code_links":1,"syntology":null},{"paper":"/paper/collateral-facilitation-in-humans-and","slug":"collateral-facilitation-in-humans-and","title":"Collateral facilitation in humans and language models","date":"2022-11-09","arxiv_id":"2211.05198","n_code_links":1,"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":["jmichaelov/collateral-facilitation"],"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/active-example-selection-for-in-context","slug":"active-example-selection-for-in-context","title":"Active Example Selection for In-Context Learning","date":"2022-11-08","arxiv_id":"2211.04486","n_code_links":1,"syntology":{"ran":10,"of":16,"n_ran_checked":4,"n_instrument":6,"unverified":6,"pointer_only":0,"phrase":"10 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 6 where Syntology's instrument failed) · 6 unverified","official":{"repos":["chicagohai/active-example-selection"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":3,"n_ran_no_instrument_failure":4,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":"/paper/interpretability-in-the-wild-a-circuit-for","slug":"interpretability-in-the-wild-a-circuit-for","title":"Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small","date":"2022-11-01","arxiv_id":"2211.00593","n_code_links":7,"syntology":{"ran":9,"of":13,"n_ran_checked":9,"n_instrument":0,"unverified":4,"pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["redwoodresearch/easy-transformer"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/text-only-training-for-image-captioning-using","slug":"text-only-training-for-image-captioning-using","title":"Text-Only Training for Image Captioning using Noise-Injected CLIP","date":"2022-11-01","arxiv_id":"2211.00575","n_code_links":4,"syntology":{"ran":4,"of":5,"n_ran_checked":2,"n_instrument":2,"unverified":1,"pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["davidhuji/capdec"],"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":["listed","official"]}}},{"paper":"/paper/ssd-lm-semi-autoregressive-simplex-based","slug":"ssd-lm-semi-autoregressive-simplex-based","title":"SSD-LM: Semi-autoregressive Simplex-based Diffusion Language Model for Text Generation and Modular Control","date":"2022-10-31","arxiv_id":"2210.17432","n_code_links":2,"syntology":null},{"paper":"/paper/probing-for-targeted-syntactic-knowledge","slug":"probing-for-targeted-syntactic-knowledge","title":"Probing for targeted syntactic knowledge through grammatical error detection","date":"2022-10-28","arxiv_id":"2210.16228","n_code_links":1,"syntology":null},{"paper":"/paper/perfectly-secure-steganography-using-minimum","slug":"perfectly-secure-steganography-using-minimum","title":"Perfectly Secure Steganography Using Minimum Entropy Coupling","date":"2022-10-24","arxiv_id":"2210.14889","n_code_links":2,"syntology":{"ran":1,"of":4,"n_ran_checked":1,"n_instrument":0,"unverified":3,"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) · 3 unverified","official":{"repos":["schroederdewitt/perfectly-secure-steganography"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":null,"slug":"team-flow-at-drc2022-pipeline-system-for","title":"Team Flow at DRC2022: Pipeline System for Travel Destination Recommendation Task in Spoken Dialogue","date":"2022-10-18","arxiv_id":"2210.09518","n_code_links":0,"syntology":null},{"paper":"/paper/a-generative-user-simulator-with-gpt-based","slug":"a-generative-user-simulator-with-gpt-based","title":"A Generative User Simulator with GPT-based Architecture and Goal State Tracking for Reinforced Multi-Domain Dialog Systems","date":"2022-10-17","arxiv_id":"2210.08692","n_code_links":1,"syntology":{"ran":8,"of":9,"n_ran_checked":8,"n_instrument":0,"unverified":1,"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) · 1 unverified","official":{"repos":["thu-spmi/gus"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/john-is-50-years-old-can-his-son-be-65","slug":"john-is-50-years-old-can-his-son-be-65","title":"\"John is 50 years old, can his son be 65?\" Evaluating NLP Models' Understanding of Feasibility","date":"2022-10-14","arxiv_id":"2210.07471","n_code_links":1,"syntology":null},{"paper":null,"slug":"jointly-reinforced-user-simulator-and-task-1","title":"Jointly Reinforced User Simulator and Task-oriented Dialog System with Simplified Generative Architecture","date":"2022-10-13","arxiv_id":"2210.06706","n_code_links":0,"syntology":null},{"paper":"/paper/predictive-querying-for-autoregressive-neural","slug":"predictive-querying-for-autoregressive-neural","title":"Predictive Querying for Autoregressive Neural Sequence Models","date":"2022-10-12","arxiv_id":"2210.06464","n_code_links":1,"syntology":{"ran":7,"of":13,"n_ran_checked":2,"n_instrument":5,"unverified":6,"pointer_only":0,"phrase":"7 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; 5 where Syntology's instrument failed) · 6 unverified","official":{"repos":["ajboyd2/prob_seq_queries"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"sumbot-summarizing-context-in-open-domain","title":"SUMBot: Summarizing Context in Open-Domain Dialogue Systems","date":"2022-10-12","arxiv_id":"2210.06496","n_code_links":0,"syntology":null},{"paper":"/paper/fine-tuning-pre-trained-transformers-into","slug":"fine-tuning-pre-trained-transformers-into","title":"Fine-Tuning Pre-trained Transformers into Decaying Fast Weights","date":"2022-10-09","arxiv_id":"2210.04243","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 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; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["jenni-ai/t2fw"],"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":null,"slug":"alphatuning-quantization-aware-parameter","title":"AlphaTuning: Quantization-Aware Parameter-Efficient Adaptation of Large-Scale Pre-Trained Language Models","date":"2022-10-08","arxiv_id":"2210.03858","n_code_links":0,"syntology":null},{"paper":"/paper/smallcap-lightweight-image-captioning","slug":"smallcap-lightweight-image-captioning","title":"SmallCap: Lightweight Image Captioning Prompted with Retrieval Augmentation","date":"2022-09-30","arxiv_id":"2209.15323","n_code_links":1,"syntology":null},{"paper":null,"slug":"dfx-a-low-latency-multi-fpga-appliance-for","title":"DFX: A Low-latency Multi-FPGA Appliance for Accelerating Transformer-based Text Generation","date":"2022-09-22","arxiv_id":"2209.10797","n_code_links":0,"syntology":null},{"paper":null,"slug":"text-revealer-private-text-reconstruction-via","title":"Text Revealer: Private Text Reconstruction via Model Inversion Attacks against Transformers","date":"2022-09-21","arxiv_id":"2209.10505","n_code_links":0,"syntology":null},{"paper":null,"slug":"chain-of-explanation-new-prompting-method-to","title":"Chain of Explanation: New Prompting Method to Generate Higher Quality Natural Language Explanation for Implicit Hate Speech","date":"2022-09-11","arxiv_id":"2209.04889","n_code_links":0,"syntology":null},{"paper":null,"slug":"why-so-toxic-measuring-and-triggering-toxic","title":"Why So Toxic? Measuring and Triggering Toxic Behavior in Open-Domain Chatbots","date":"2022-09-07","arxiv_id":"2209.03463","n_code_links":0,"syntology":null},{"paper":null,"slug":"every-picture-tells-a-story-image-grounded","title":"Every picture tells a story: Image-grounded controllable stylistic story generation","date":"2022-09-04","arxiv_id":"2209.01638","n_code_links":0,"syntology":null},{"paper":"/paper/adan-adaptive-nesterov-momentum-algorithm-for","slug":"adan-adaptive-nesterov-momentum-algorithm-for","title":"Adan: Adaptive Nesterov Momentum Algorithm for Faster Optimizing Deep Models","date":"2022-08-13","arxiv_id":"2208.06677","n_code_links":9,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"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","official":{"repos":["sail-sg/adan"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":null,"slug":"studying-writer-suggestion-interaction-a","title":"Interacting with next-phrase suggestions: How suggestion systems aid and influence the cognitive processes of writing","date":"2022-08-01","arxiv_id":"2208.00636","n_code_links":0,"syntology":null},{"paper":"/paper/zero-shot-video-captioning-with-evolving","slug":"zero-shot-video-captioning-with-evolving","title":"Zero-Shot Video Captioning with Evolving Pseudo-Tokens","date":"2022-07-22","arxiv_id":"2207.11100","n_code_links":1,"syntology":null},{"paper":null,"slug":"word-play-for-playing-othello-reverses","title":"Word Play for Playing Othello (Reverses)","date":"2022-07-18","arxiv_id":"2207.08766","n_code_links":0,"syntology":null},{"paper":null,"slug":"active-data-pattern-extraction-attacks-on","title":"Combing for Credentials: Active Pattern Extraction from Smart Reply","date":"2022-07-14","arxiv_id":"2207.10802","n_code_links":0,"syntology":null},{"paper":null,"slug":"hidden-schema-networks","title":"Hidden Schema Networks","date":"2022-07-08","arxiv_id":"2207.03777","n_code_links":0,"syntology":null},{"paper":null,"slug":"neural-language-models-are-not-born-equal-to","title":"Neural Language Models are not Born Equal to Fit Brain Data, but Training Helps","date":"2022-07-07","arxiv_id":"2207.03380","n_code_links":0,"syntology":null},{"paper":null,"slug":"sensitivity-analysis-on-transferred-neural","title":"Sensitivity Analysis on Transferred Neural Architectures of BERT and GPT-2 for Financial Sentiment Analysis","date":"2022-07-07","arxiv_id":"2207.03037","n_code_links":0,"syntology":null},{"paper":"/paper/materials-transformers-language-models-for","slug":"materials-transformers-language-models-for","title":"Materials Transformers Language Models for Generative Materials Design: a benchmark study","date":"2022-06-27","arxiv_id":"2206.13578","n_code_links":1,"syntology":null},{"paper":null,"slug":"differentially-private-model-compression","title":"Differentially Private Model Compression","date":"2022-06-03","arxiv_id":"2206.01838","n_code_links":0,"syntology":null},{"paper":null,"slug":"romantic-computing","title":"Romantic-Computing","date":"2022-06-01","arxiv_id":"2206.11864","n_code_links":0,"syntology":null},{"paper":"/paper/flashattention-fast-and-memory-efficient","slug":"flashattention-fast-and-memory-efficient","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","date":"2022-05-27","arxiv_id":"2205.14135","n_code_links":13,"syntology":{"ran":24,"of":30,"n_ran_checked":18,"n_instrument":6,"unverified":6,"pointer_only":1,"phrase":"24 ran (of which 2 constructed an object rather than computing a result; 18 with no instrument failure: 0 honoured, 1 violated, 17 with no contract checked; 6 where Syntology's instrument failed) · 6 unverified","official":{"repos":["dao-ailab/flash-attention"],"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","listed"]}}},{"paper":"/paper/nearest-neighbor-zero-shot-inference","slug":"nearest-neighbor-zero-shot-inference","title":"kNN-Prompt: Nearest Neighbor Zero-Shot Inference","date":"2022-05-27","arxiv_id":"2205.13792","n_code_links":1,"syntology":null},{"paper":"/paper/garden-path-traversal-within-gpt-2","slug":"garden-path-traversal-within-gpt-2","title":"Garden-Path Traversal in GPT-2","date":"2022-05-24","arxiv_id":"2205.12302","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"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) · 0 unverified","official":{"repos":["wjurayj/garden-path-gpt2"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/towards-understanding-gender-seniority","slug":"towards-understanding-gender-seniority","title":"Towards Understanding Gender-Seniority Compound Bias in Natural Language Generation","date":"2022-05-19","arxiv_id":"2205.09830","n_code_links":1,"syntology":null},{"paper":null,"slug":"evaluation-of-transfer-learning-for-polish-1","title":"Evaluation of Transfer Learning for Polish with a Text-to-Text Model","date":"2022-05-18","arxiv_id":"2205.08808","n_code_links":0,"syntology":null},{"paper":"/paper/what-gpt-knows-about-who-is-who-1","slug":"what-gpt-knows-about-who-is-who-1","title":"What GPT Knows About Who is Who","date":"2022-05-16","arxiv_id":"2205.07407","n_code_links":1,"syntology":null},{"paper":"/paper/naturalistic-causal-probing-for-morpho-syntax","slug":"naturalistic-causal-probing-for-morpho-syntax","title":"Naturalistic Causal Probing for Morpho-Syntax","date":"2022-05-14","arxiv_id":"2205.07043","n_code_links":1,"syntology":null},{"paper":null,"slug":"ratatouille-a-tool-for-novel-recipe","title":"Ratatouille: A tool for Novel Recipe Generation","date":"2022-05-10","arxiv_id":"2206.08267","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-segment-preserving-sampling-for-deep","title":"Multi-segment preserving sampling for deep manifold sampler","date":"2022-05-09","arxiv_id":"2205.04259","n_code_links":0,"syntology":null},{"paper":"/paper/when-a-sentence-does-not-introduce-a-1","slug":"when-a-sentence-does-not-introduce-a-1","title":"When a sentence does not introduce a discourse entity, Transformer-based models still sometimes refer to it","date":"2022-05-06","arxiv_id":"2205.03472","n_code_links":1,"syntology":null},{"paper":null,"slug":"tailor-a-prompt-based-approach-to-attribute","title":"Tailor: A Prompt-Based Approach to Attribute-Based Controlled Text Generation","date":"2022-04-28","arxiv_id":"2204.13362","n_code_links":0,"syntology":null},{"paper":null,"slug":"zero-shot-entity-and-tweet-characterization","title":"Zero-shot Entity and Tweet Characterization with Designed Conditional Prompts and Contexts","date":"2022-04-18","arxiv_id":"2204.08405","n_code_links":0,"syntology":null},{"paper":"/paper/mgpt-few-shot-learners-go-multilingual","slug":"mgpt-few-shot-learners-go-multilingual","title":"mGPT: Few-Shot Learners Go Multilingual","date":"2022-04-15","arxiv_id":"2204.07580","n_code_links":1,"syntology":null},{"paper":null,"slug":"brazilian-court-documents-clustered-by","title":"Analysing similarities between legal court documents using natural language processing approaches based on Transformers","date":"2022-04-14","arxiv_id":"2204.07182","n_code_links":0,"syntology":null},{"paper":"/paper/uniform-complexity-for-text-generation","slug":"uniform-complexity-for-text-generation","title":"Uniform Complexity for Text Generation","date":"2022-04-11","arxiv_id":"2204.05185","n_code_links":1,"syntology":null},{"paper":null,"slug":"accelerating-attention-through-gradient-based","title":"Accelerating Attention through Gradient-Based Learned Runtime Pruning","date":"2022-04-07","arxiv_id":"2204.03227","n_code_links":0,"syntology":null},{"paper":"/paper/testing-the-limits-of-natural-language-models","slug":"testing-the-limits-of-natural-language-models","title":"Testing the limits of natural language models for predicting human language judgments","date":"2022-04-07","arxiv_id":"2204.03592","n_code_links":1,"syntology":null},{"paper":"/paper/knowledge-infused-decoding-1","slug":"knowledge-infused-decoding-1","title":"Knowledge Infused Decoding","date":"2022-04-06","arxiv_id":"2204.03084","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":["microsoft/kid"],"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"]}}},{"paper":null,"slug":"effect-and-analysis-of-large-scale-language","title":"Effect and Analysis of Large-scale Language Model Rescoring on Competitive ASR Systems","date":"2022-04-01","arxiv_id":"2204.00212","n_code_links":0,"syntology":null},{"paper":"/paper/monarch-expressive-structured-matrices-for","slug":"monarch-expressive-structured-matrices-for","title":"Monarch: Expressive Structured Matrices for Efficient and Accurate Training","date":"2022-04-01","arxiv_id":"2204.00595","n_code_links":2,"syntology":{"ran":15,"of":15,"n_ran_checked":14,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 1 violated, 13 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["hazyresearch/monarch"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/a-slot-is-not-built-in-one-utterance-spoken-1","slug":"a-slot-is-not-built-in-one-utterance-spoken-1","title":"A Slot Is Not Built in One Utterance: Spoken Language Dialogs with Sub-Slots","date":"2022-03-21","arxiv_id":"2203.10759","n_code_links":1,"syntology":null},{"paper":null,"slug":"compression-of-generative-pre-trained","title":"Compression of Generative Pre-trained Language Models via Quantization","date":"2022-03-21","arxiv_id":"2203.10705","n_code_links":0,"syntology":null},{"paper":"/paper/dependency-based-mixture-language-models","slug":"dependency-based-mixture-language-models","title":"Dependency-based Mixture Language Models","date":"2022-03-19","arxiv_id":"2203.10256","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":2,"n_instrument":1,"unverified":1,"pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["fadedcosine/dependency-guided-neural-text-generation"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"are-you-robert-or-roberta-deceiving-online","title":"Are You Robert or RoBERTa? Deceiving Online Authorship Attribution Models Using Neural Text Generators","date":"2022-03-18","arxiv_id":"2203.09813","n_code_links":0,"syntology":null},{"paper":"/paper/do-language-models-plagiarize","slug":"do-language-models-plagiarize","title":"Do Language Models Plagiarize?","date":"2022-03-15","arxiv_id":"2203.07618","n_code_links":1,"syntology":null},{"paper":null,"slug":"contrastive-visual-semantic-pretraining","title":"Contrastive Visual Semantic Pretraining Magnifies the Semantics of Natural Language Representations","date":"2022-03-14","arxiv_id":"2203.07511","n_code_links":0,"syntology":null},{"paper":"/paper/vast-the-valence-assessing-semantics-test-for","slug":"vast-the-valence-assessing-semantics-test-for","title":"VAST: The Valence-Assessing Semantics Test for Contextualizing Language Models","date":"2022-03-14","arxiv_id":"2203.07504","n_code_links":1,"syntology":null},{"paper":"/paper/block-sparse-adversarial-attack-to-fool","slug":"block-sparse-adversarial-attack-to-fool","title":"Block-Sparse Adversarial Attack to Fool Transformer-Based Text Classifiers","date":"2022-03-11","arxiv_id":"2203.05948","n_code_links":1,"syntology":null},{"paper":"/paper/when-classifying-grammatical-role-bert-doesn-1","slug":"when-classifying-grammatical-role-bert-doesn-1","title":"When classifying grammatical role, BERT doesn't care about word order... except when it matters","date":"2022-03-11","arxiv_id":"2203.06204","n_code_links":1,"syntology":null},{"paper":"/paper/litetransformersearch-training-free-on-device","slug":"litetransformersearch-training-free-on-device","title":"LiteTransformerSearch: Training-free Neural Architecture Search for Efficient Language Models","date":"2022-03-04","arxiv_id":"2203.02094","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":5,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["microsoft/archai"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/parameter-efficient-mixture-of-experts","slug":"parameter-efficient-mixture-of-experts","title":"Parameter-Efficient Mixture-of-Experts Architecture for Pre-trained Language Models","date":"2022-03-02","arxiv_id":"2203.01104","n_code_links":2,"syntology":{"ran":5,"of":5,"n_ran_checked":3,"n_instrument":2,"unverified":0,"pointer_only":0,"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","official":{"repos":["rucaibox/mpo","rucaibox/mpoe"],"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"]}}},{"paper":"/paper/a-systematic-evaluation-of-large-language","slug":"a-systematic-evaluation-of-large-language","title":"A Systematic Evaluation of Large Language Models of Code","date":"2022-02-26","arxiv_id":"2202.13169","n_code_links":3,"syntology":{"ran":2,"of":3,"n_ran_checked":1,"n_instrument":1,"unverified":1,"pointer_only":0,"phrase":"2 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; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["eleutherai/gpt-neox","vhellendoorn/code-lms"],"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"]}}},{"paper":null,"slug":"defending-against-reconstruction-attacks-with","title":"Defending against Reconstruction Attacks with Rényi Differential Privacy","date":"2022-02-15","arxiv_id":"2202.07623","n_code_links":0,"syntology":null},{"paper":"/paper/maximizing-communication-efficiency-for-large","slug":"maximizing-communication-efficiency-for-large","title":"Maximizing Communication Efficiency for Large-scale Training via 0/1 Adam","date":"2022-02-12","arxiv_id":"2202.06009","n_code_links":1,"syntology":null},{"paper":"/paper/a-benchmark-corpus-for-the-detection-of","slug":"a-benchmark-corpus-for-the-detection-of","title":"A Benchmark Corpus for the Detection of Automatically Generated Text in Academic Publications","date":"2022-02-04","arxiv_id":"2202.02013","n_code_links":1,"syntology":null},{"paper":null,"slug":"pre-trained-language-transformers-are","title":"Pre-Trained Language Transformers are Universal Image Classifiers","date":"2022-01-25","arxiv_id":"2201.10182","n_code_links":0,"syntology":null},{"paper":null,"slug":"synthetic-books","title":"Synthetic Books","date":"2022-01-24","arxiv_id":"2201.09518","n_code_links":0,"syntology":null},{"paper":null,"slug":"auto-regressive-text-generation-with-pre","title":"Auto-regressive Text Generation with Pre-Trained Language Models: An Empirical Study on Question-type Short Text Generation","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null}],"record_sha256":"26e7b78f8cb65ea5efe8db66371f136f66985007f8ee83ca3020f12aa0cfff82","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}