{"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/discriminative-fine-tuning/papers/15","list_of":"/method/discriminative-fine-tuning","method":"Discriminative Fine-Tuning","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":15,"pages_in_order":20,"rows_per_page":100,"rows":[1401,1500],"of":1990,"counts":{"archive_papers_tagged":1990,"with_a_code_link":794,"where_syntology_ran_a_sample":271,"not_listed_spam_title":0,"listed":1990,"listed_where_code_ran":271,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":223,"every_run_a_failure_of_syntologys_instrument":48,"listed_with_a_run_with_no_instrument_failure":223,"listed_every_run_a_failure_of_syntologys_instrument":48,"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/discriminative-fine-tuning","prev":"/method/discriminative-fine-tuning/papers/14","next":"/method/discriminative-fine-tuning/papers/16","papers":[{"paper":"/paper/evaluation-of-chatgpt-as-a-question-answering","slug":"evaluation-of-chatgpt-as-a-question-answering","title":"Can ChatGPT Replace Traditional KBQA Models? An In-depth Analysis of the Question Answering Performance of the GPT LLM Family","date":"2023-03-14","arxiv_id":"2303.07992","n_code_links":2,"syntology":null},{"paper":null,"slug":"learning-combinatorial-prompts-for-universal","title":"Learning Combinatorial Prompts for Universal Controllable Image Captioning","date":"2023-03-11","arxiv_id":"2303.06338","n_code_links":0,"syntology":null},{"paper":null,"slug":"algorithmic-ghost-in-the-research-shell-large","title":"Algorithmic Ghost in the Research Shell: Large Language Models and Academic Knowledge Creation in Management Research","date":"2023-03-10","arxiv_id":"2303.07304","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-models-gpt-struggle-to-answer","title":"Large Language Models (GPT) Struggle to Answer Multiple-Choice Questions about Code","date":"2023-03-09","arxiv_id":"2303.08033","n_code_links":0,"syntology":null},{"paper":"/paper/on-the-risks-of-stealing-the-decoding","slug":"on-the-risks-of-stealing-the-decoding","title":"Stealing the Decoding Algorithms of Language Models","date":"2023-03-08","arxiv_id":"2303.04729","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":"/paper/towards-zero-shot-functional-compositionality","slug":"towards-zero-shot-functional-compositionality","title":"Towards Zero-Shot Functional Compositionality of Language Models","date":"2023-03-06","arxiv_id":"2303.03103","n_code_links":1,"syntology":null},{"paper":null,"slug":"fqp-2-0-industry-trend-analysis-via","title":"Industry Risk Assessment via Hierarchical Financial Data Using Stock Market Sentiment Indicators","date":"2023-03-05","arxiv_id":"2303.02707","n_code_links":0,"syntology":null},{"paper":null,"slug":"cross-lingual-summarization-via-chatgpt","title":"Zero-Shot Cross-Lingual Summarization via Large Language Models","date":"2023-02-28","arxiv_id":"2302.14229","n_code_links":0,"syntology":null},{"paper":"/paper/information-restricted-neural-language-models","slug":"information-restricted-neural-language-models","title":"Information-Restricted Neural Language Models Reveal Different Brain Regions' Sensitivity to Semantics, Syntax and Context","date":"2023-02-28","arxiv_id":"2302.14389","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":5,"n_instrument":0,"unverified":0,"pointer_only":0,"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":["alexandrepsq/information-restrited-nlms"],"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/large-language-models-are-state-of-the-art","slug":"large-language-models-are-state-of-the-art","title":"Large Language Models Are State-of-the-Art Evaluators of Translation Quality","date":"2023-02-28","arxiv_id":"2302.14520","n_code_links":4,"syntology":null},{"paper":"/paper/inseq-an-interpretability-toolkit-for","slug":"inseq-an-interpretability-toolkit-for","title":"Inseq: An Interpretability Toolkit for Sequence Generation Models","date":"2023-02-27","arxiv_id":"2302.13942","n_code_links":2,"syntology":null},{"paper":null,"slug":"fast-attention-requires-bounded-entries","title":"Fast Attention Requires Bounded Entries","date":"2023-02-26","arxiv_id":"2302.13214","n_code_links":0,"syntology":null},{"paper":"/paper/large-scale-multi-modal-pre-trained-models-a","slug":"large-scale-multi-modal-pre-trained-models-a","title":"Large-scale Multi-Modal Pre-trained Models: A Comprehensive Survey","date":"2023-02-20","arxiv_id":"2302.10035","n_code_links":1,"syntology":null},{"paper":"/paper/how-good-are-gpt-models-at-machine","slug":"how-good-are-gpt-models-at-machine","title":"How Good Are GPT Models at Machine Translation? A Comprehensive Evaluation","date":"2023-02-18","arxiv_id":"2302.09210","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"3 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; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["microsoft/gpt-mt"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/conveying-the-predicted-future-to-users-a","slug":"conveying-the-predicted-future-to-users-a","title":"Conveying the Predicted Future to Users: A Case Study of Story Plot Prediction","date":"2023-02-17","arxiv_id":"2302.09122","n_code_links":1,"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":"foundation-models-for-natural-language","title":"Foundation Models for Natural Language Processing -- Pre-trained Language Models Integrating Media","date":"2023-02-16","arxiv_id":"2302.08575","n_code_links":0,"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":"/paper/tree-based-representation-and-generation-of","slug":"tree-based-representation-and-generation-of","title":"Tree-Based Representation and Generation of Natural and Mathematical Language","date":"2023-02-15","arxiv_id":"2302.07974","n_code_links":1,"syntology":null},{"paper":null,"slug":"artificial-intelligence-in-psychology","title":"Diminished Diversity-of-Thought in a Standard Large Language Model","date":"2023-02-13","arxiv_id":"2302.07267","n_code_links":0,"syntology":null},{"paper":null,"slug":"academic-writing-with-gpt-3-5-reflections-on","title":"Academic Writing with GPT-3.5: Reflections on Practices, Efficacy and Transparency","date":"2023-02-12","arxiv_id":"2304.11079","n_code_links":0,"syntology":null},{"paper":"/paper/combat-ai-with-ai-counteract-machine","slug":"combat-ai-with-ai-counteract-machine","title":"Combat AI With AI: Counteract Machine-Generated Fake Restaurant Reviews on Social Media","date":"2023-02-10","arxiv_id":"2302.07731","n_code_links":1,"syntology":null},{"paper":"/paper/fairpy-a-toolkit-for-evaluation-of-social","slug":"fairpy-a-toolkit-for-evaluation-of-social","title":"FairPy: A Toolkit for Evaluation of Prediction Biases and their Mitigation in Large Language Models","date":"2023-02-10","arxiv_id":"2302.05508","n_code_links":1,"syntology":null},{"paper":"/paper/the-wisdom-of-hindsight-makes-language-models","slug":"the-wisdom-of-hindsight-makes-language-models","title":"The Wisdom of Hindsight Makes Language Models Better Instruction Followers","date":"2023-02-10","arxiv_id":"2302.05206","n_code_links":1,"syntology":null},{"paper":"/paper/translating-natural-language-to-planning","slug":"translating-natural-language-to-planning","title":"Translating Natural Language to Planning Goals with Large-Language Models","date":"2023-02-10","arxiv_id":"2302.05128","n_code_links":1,"syntology":null},{"paper":null,"slug":"better-by-you-better-than-me-chatgpt3-as","title":"Better by you, better than me, chatgpt3 as writing assistance in students essays","date":"2023-02-09","arxiv_id":"2302.04536","n_code_links":0,"syntology":null},{"paper":null,"slug":"nationality-bias-in-text-generation","title":"Nationality Bias in Text Generation","date":"2023-02-05","arxiv_id":"2302.02463","n_code_links":0,"syntology":null},{"paper":null,"slug":"quantized-distributed-training-of-large","title":"Quantized Distributed Training of Large Models with Convergence Guarantees","date":"2023-02-05","arxiv_id":"2302.02390","n_code_links":0,"syntology":null},{"paper":"/paper/realtabformer-generating-realistic-relational","slug":"realtabformer-generating-realistic-relational","title":"REaLTabFormer: Generating Realistic Relational and Tabular Data using Transformers","date":"2023-02-04","arxiv_id":"2302.02041","n_code_links":3,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"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) · 1 unverified","official":{"repos":["avsolatorio/realtabformer"],"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":"/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":null,"slug":"what-language-reveals-about-perception","title":"Large language models predict human sensory judgments across six modalities","date":"2023-02-02","arxiv_id":"2302.01308","n_code_links":0,"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/large-language-models-are-latent-variable-1","slug":"large-language-models-are-latent-variable-1","title":"Large Language Models Are Latent Variable Models: Explaining and Finding Good Demonstrations for In-Context Learning","date":"2023-01-27","arxiv_id":"2301.11916","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":0,"n_instrument":1,"unverified":1,"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) · 1 unverified","official":{"repos":["wangxinyilinda/concept-based-demonstration-selection"],"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"]}}},{"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":"/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":"/paper/t2m-gpt-generating-human-motion-from-textual","slug":"t2m-gpt-generating-human-motion-from-textual","title":"T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations","date":"2023-01-15","arxiv_id":"2301.06052","n_code_links":1,"syntology":{"ran":5,"of":7,"n_ran_checked":5,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"5 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["Mael-zys/T2M-GPT"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":4,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/gpt-as-knowledge-worker-a-zero-shot","slug":"gpt-as-knowledge-worker-a-zero-shot","title":"GPT as Knowledge Worker: A Zero-Shot Evaluation of (AI)CPA Capabilities","date":"2023-01-11","arxiv_id":"2301.04408","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":"generating-human-motion-from-textual","title":"Generating Human Motion From Textual Descriptions With Discrete Representations","date":"2023-01-01","arxiv_id":null,"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":"/paper/gpt-takes-the-bar-exam","slug":"gpt-takes-the-bar-exam","title":"GPT Takes the Bar Exam","date":"2022-12-29","arxiv_id":"2212.14402","n_code_links":5,"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":"/paper/benchmark-for-uncertainty-robustness-in-self","slug":"benchmark-for-uncertainty-robustness-in-self","title":"Benchmark for Uncertainty & Robustness in Self-Supervised Learning","date":"2022-12-23","arxiv_id":"2212.12411","n_code_links":1,"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":null,"slug":"kl-regularized-normalization-framework-for","title":"KL Regularized Normalization Framework for Low Resource Tasks","date":"2022-12-21","arxiv_id":"2212.11275","n_code_links":0,"syntology":null},{"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":null,"slug":"true-detective-a-challenging-benchmark-for","title":"True Detective: A Deep Abductive Reasoning Benchmark Undoable for GPT-3 and Challenging for GPT-4","date":"2022-12-20","arxiv_id":"2212.10114","n_code_links":0,"syntology":null},{"paper":"/paper/why-can-gpt-learn-in-context-language-models","slug":"why-can-gpt-learn-in-context-language-models","title":"Why Can GPT Learn In-Context? Language Models Implicitly Perform Gradient Descent as Meta-Optimizers","date":"2022-12-20","arxiv_id":"2212.10559","n_code_links":1,"syntology":null},{"paper":"/paper/reasoning-with-language-model-prompting-a","slug":"reasoning-with-language-model-prompting-a","title":"Reasoning with Language Model Prompting: A Survey","date":"2022-12-19","arxiv_id":"2212.09597","n_code_links":2,"syntology":null},{"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":"audio-driven-co-speech-gesture-video","title":"Audio-Driven Co-Speech Gesture Video Generation","date":"2022-12-05","arxiv_id":"2212.02350","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":null,"slug":"outfit-generation-and-recommendation-an","title":"Outfit Generation and Recommendation -- An Experimental Study","date":"2022-11-29","arxiv_id":"2211.16353","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":"/paper/pointclip-v2-adapting-clip-for-powerful-3d","slug":"pointclip-v2-adapting-clip-for-powerful-3d","title":"PointCLIP V2: Prompting CLIP and GPT for Powerful 3D Open-world Learning","date":"2022-11-21","arxiv_id":"2211.11682","n_code_links":2,"syntology":{"ran":8,"of":12,"n_ran_checked":4,"n_instrument":4,"unverified":4,"pointer_only":4,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified","official":{"repos":["yangyangyang127/pointclip_v2"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"conceptor-aided-debiasing-of-contextualized","title":"Conceptor-Aided Debiasing of Large Language Models","date":"2022-11-20","arxiv_id":"2211.11087","n_code_links":0,"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":"/paper/random-ltd-random-and-layerwise-token","slug":"random-ltd-random-and-layerwise-token","title":"Random-LTD: Random and Layerwise Token Dropping Brings Efficient Training for Large-scale Transformers","date":"2022-11-17","arxiv_id":"2211.11586","n_code_links":1,"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/gptq-accurate-post-training-quantization-for","slug":"gptq-accurate-post-training-quantization-for","title":"GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers","date":"2022-10-31","arxiv_id":"2210.17323","n_code_links":17,"syntology":{"ran":5,"of":15,"n_ran_checked":2,"n_instrument":3,"unverified":10,"pointer_only":1,"phrase":"5 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; 3 where Syntology's instrument failed) · 10 unverified","official":{"repos":["ist-daslab/gptq"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"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":null,"slug":"trscore-a-novel-gpt-based-readability-scorer","title":"TRScore: A Novel GPT-based Readability Scorer for ASR Segmentation and Punctuation model evaluation and selection","date":"2022-10-27","arxiv_id":"2210.15104","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-robustness-of-prefix-tuning-in","title":"Exploring Robustness of Prefix Tuning in Noisy Data: A Case Study in Financial Sentiment Analysis","date":"2022-10-26","arxiv_id":"2211.05584","n_code_links":0,"syntology":null},{"paper":null,"slug":"ielm-an-open-information-extraction-benchmark","title":"IELM: An Open Information Extraction Benchmark for Pre-Trained Language Models","date":"2022-10-25","arxiv_id":"2210.14128","n_code_links":0,"syntology":null},{"paper":"/paper/emergent-world-representations-exploring-a","slug":"emergent-world-representations-exploring-a","title":"Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task","date":"2022-10-24","arxiv_id":"2210.13382","n_code_links":4,"syntology":{"ran":6,"of":6,"n_ran_checked":5,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"6 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; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["likenneth/othello_world"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"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":"meta-learning-pathologies-from-radiology","title":"Meta-learning Pathologies from Radiology Reports using Variance Aware Prototypical Networks","date":"2022-10-22","arxiv_id":"2210.13979","n_code_links":0,"syntology":null},{"paper":"/paper/a-causal-framework-to-quantify-the-robustness","slug":"a-causal-framework-to-quantify-the-robustness","title":"A Causal Framework to Quantify the Robustness of Mathematical Reasoning with Language Models","date":"2022-10-21","arxiv_id":"2210.12023","n_code_links":1,"syntology":{"ran":5,"of":7,"n_ran_checked":3,"n_instrument":2,"unverified":2,"pointer_only":7,"phrase":"5 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["alestolfo/causal-math"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/general-image-descriptors-for-open-world","slug":"general-image-descriptors-for-open-world","title":"General Image Descriptors for Open World Image Retrieval using ViT CLIP","date":"2022-10-20","arxiv_id":"2210.11141","n_code_links":1,"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":["ivanaer/g-universal-clip"],"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/biogpt-generative-pre-trained-transformer-for","slug":"biogpt-generative-pre-trained-transformer-for","title":"BioGPT: Generative Pre-trained Transformer for Biomedical Text Generation and Mining","date":"2022-10-19","arxiv_id":"2210.10341","n_code_links":4,"syntology":null},{"paper":null,"slug":"towards-a-neural-architecture-of-language","title":"Towards a neural architecture of language: Deep learning versus logistics of access in neural architectures for compositional processing","date":"2022-10-19","arxiv_id":"2210.10543","n_code_links":0,"syntology":null},{"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/dylora-parameter-efficient-tuning-of-pre","slug":"dylora-parameter-efficient-tuning-of-pre","title":"DyLoRA: Parameter Efficient Tuning of Pre-trained Models using Dynamic Search-Free Low-Rank Adaptation","date":"2022-10-14","arxiv_id":"2210.07558","n_code_links":2,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":{"repos":["huawei-noah/kd-nlp"],"state":"official: not harvested","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]}}},{"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/foundation-transformers","slug":"foundation-transformers","title":"Foundation Transformers","date":"2022-10-12","arxiv_id":"2210.06423","n_code_links":4,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"pointer_only":0,"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) · 1 unverified","official":{"repos":["microsoft/unilm"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}],"record_sha256":"ea6811b70e063918421ea085de444b4f68e2593d128df3e5099c9215df8d82c7","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}