{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/language-modeling/papers/105","list_of":"/task/language-modeling","task":"Language Modeling","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":105,"pages_in_order":142,"rows_per_page":100,"rows":[10401,10500],"of":14182,"counts":{"archive_papers_tagged":14182,"with_a_code_link":5620,"where_syntology_ran_a_sample":1894,"not_listed_spam_title":0,"listed":14182,"listed_where_code_ran":1894,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1580,"every_run_a_failure_of_syntologys_instrument":314,"listed_with_a_run_with_no_instrument_failure":1580,"listed_every_run_a_failure_of_syntologys_instrument":314,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/language-modeling","prev":"/task/language-modeling/papers/104","next":"/task/language-modeling/papers/106","papers":[{"url":null,"slug":"doremi-grounding-language-model-by-detecting","title":"DoReMi: Grounding Language Model by Detecting and Recovering from Plan-Execution Misalignment","date":"2023-07-01","arxiv_id":"2307.00329","repositories_listed":0,"syntology":null},{"url":null,"slug":"thuir2-at-ntcir-16-session-search-ss-task","title":"THUIR2 at NTCIR-16 Session Search (SS) Task","date":"2023-07-01","arxiv_id":"2307.00250","repositories_listed":0,"syntology":null},{"url":"/paper/stay-on-topic-with-classifier-free-guidance","slug":"stay-on-topic-with-classifier-free-guidance","title":"Stay on topic with Classifier-Free Guidance","date":"2023-06-30","arxiv_id":"2306.17806","repositories_listed":0,"syntology":null},{"url":null,"slug":"ticket-bert-labeling-incident-management","title":"Ticket-BERT: Labeling Incident Management Tickets with Language Models","date":"2023-06-30","arxiv_id":"2307.00108","repositories_listed":0,"syntology":null},{"url":null,"slug":"benchmarking-large-language-model","title":"Benchmarking Large Language Model Capabilities for Conditional Generation","date":"2023-06-29","arxiv_id":"2306.16793","repositories_listed":0,"syntology":null},{"url":null,"slug":"cmath-can-your-language-model-pass-chinese","title":"CMATH: Can Your Language Model Pass Chinese Elementary School Math Test?","date":"2023-06-29","arxiv_id":"2306.16636","repositories_listed":0,"syntology":null},{"url":null,"slug":"modeling-parallel-programs-using-large","title":"HPC-Coder: Modeling Parallel Programs using Large Language Models","date":"2023-06-29","arxiv_id":"2306.17281","repositories_listed":0,"syntology":null},{"url":null,"slug":"rapgen-an-approach-for-fixing-code","title":"RAPGen: An Approach for Fixing Code Inefficiencies in Zero-Shot","date":"2023-06-29","arxiv_id":"2306.17077","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-open-domain-topic-classification-1","title":"Towards Open-Domain Topic Classification","date":"2023-06-29","arxiv_id":"2306.17290","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-adversarial-multi-task-learning-method-for","title":"An Adversarial Multi-Task Learning Method for Chinese Text Correction with Semantic Detection","date":"2023-06-28","arxiv_id":"2306.16313","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-calibration-and-error-correction","title":"Pareto Optimal Learning for Estimating Large Language Model Errors","date":"2023-06-28","arxiv_id":"2306.16564","repositories_listed":0,"syntology":null},{"url":null,"slug":"prompting-large-language-models-for-zero-shot","title":"Prompting Large Language Models for Zero-Shot Domain Adaptation in Speech Recognition","date":"2023-06-28","arxiv_id":"2306.16007","repositories_listed":0,"syntology":null},{"url":null,"slug":"flurka-fast-fused-low-rank-kernel-attention","title":"FLuRKA: Fast and accurate unified Low-Rank & Kernel Attention","date":"2023-06-27","arxiv_id":"2306.15799","repositories_listed":0,"syntology":null},{"url":null,"slug":"paradigm-shift-in-sustainability-disclosure","title":"Paradigm Shift in Sustainability Disclosure Analysis: Empowering Stakeholders with CHATREPORT, a Language Model-Based Tool","date":"2023-06-27","arxiv_id":"2306.15518","repositories_listed":0,"syntology":null},{"url":null,"slug":"using-large-language-models-to-provide","title":"Using Large Language Models to Provide Explanatory Feedback to Human Tutors","date":"2023-06-27","arxiv_id":"2306.15498","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-assessment-of-divergent-thinking-in","title":"Automatic Assessment of Divergent Thinking in Chinese Language with TransDis: A Transformer-Based Language Model Approach","date":"2023-06-26","arxiv_id":"2306.14790","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-multimodal-models-notes-on-cvpr-2023","title":"Large Multimodal Models: Notes on CVPR 2023 Tutorial","date":"2023-06-26","arxiv_id":"2306.14895","repositories_listed":0,"syntology":null},{"url":null,"slug":"lm4hpc-towards-effective-language-model","title":"LM4HPC: Towards Effective Language Model Application in High-Performance Computing","date":"2023-06-26","arxiv_id":"2306.14979","repositories_listed":0,"syntology":null},{"url":null,"slug":"transfer-learning-across-several-centuries","title":"Transfer Learning across Several Centuries: Machine and Historian Integrated Method to Decipher Royal Secretary's Diary","date":"2023-06-26","arxiv_id":"2306.14592","repositories_listed":0,"syntology":null},{"url":null,"slug":"interactive-design-by-integrating-a-large-pre","title":"Interactive Design by Integrating a Large Pre-Trained Language Model and Building Information Modeling","date":"2023-06-25","arxiv_id":"2306.14165","repositories_listed":0,"syntology":null},{"url":null,"slug":"low-rank-prune-and-factorize-for-language","title":"Low-Rank Prune-And-Factorize for Language Model Compression","date":"2023-06-25","arxiv_id":"2306.14152","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-neuro-symbolic-inverse-planning-engine","title":"The Neuro-Symbolic Inverse Planning Engine (NIPE): Modeling Probabilistic Social Inferences from Linguistic Inputs","date":"2023-06-25","arxiv_id":"2306.14325","repositories_listed":0,"syntology":null},{"url":null,"slug":"spatio-temporal-storytelling-leveraging","title":"Spatio-temporal Storytelling? Leveraging Generative Models for Semantic Trajectory Analysis","date":"2023-06-24","arxiv_id":"2306.13905","repositories_listed":0,"syntology":null},{"url":null,"slug":"multimodal-search-on-iconclass-using-vision","title":"Multimodal Search on Iconclass using Vision-Language Pre-Trained Models","date":"2023-06-23","arxiv_id":"2306.16529","repositories_listed":0,"syntology":null},{"url":null,"slug":"apolitical-intelligence-auditing-delphi-s","title":"Apolitical Intelligence? Auditing Delphi's responses on controversial political issues in the US","date":"2023-06-22","arxiv_id":"2306.13000","repositories_listed":0,"syntology":null},{"url":null,"slug":"audiopalm-a-large-language-model-that-can","title":"AudioPaLM: A Large Language Model That Can Speak and Listen","date":"2023-06-22","arxiv_id":"2306.12925","repositories_listed":0,"syntology":null},{"url":null,"slug":"beyond-chemical-language-a-multimodal","title":"Beyond Chemical Language: A Multimodal Approach to Enhance Molecular Property Prediction","date":"2023-06-22","arxiv_id":"2306.14919","repositories_listed":0,"syntology":null},{"url":null,"slug":"implicit-spoken-language-diarization","title":"Implicit spoken language diarization","date":"2023-06-22","arxiv_id":"2306.12913","repositories_listed":0,"syntology":null},{"url":null,"slug":"iterated-piecewise-affine-ipa-approximation","title":"Iterated Piecewise Affine (IPA) Approximation for Language Modeling","date":"2023-06-21","arxiv_id":"2306.12317","repositories_listed":0,"syntology":null},{"url":null,"slug":"solving-dialogue-grounding-embodied-task-in-a","title":"Solving Dialogue Grounding Embodied Task in a Simulated Environment using Further Masked Language Modeling","date":"2023-06-21","arxiv_id":"2306.12387","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-novel-counterfactual-method-for-aspect","title":"A Novel Counterfactual Data Augmentation Method for Aspect-Based Sentiment Analysis","date":"2023-06-20","arxiv_id":"2306.11260","repositories_listed":0,"syntology":null},{"url":null,"slug":"chatgpt-is-not-enough-enhancing-large","title":"Give Us the Facts: Enhancing Large Language Models with Knowledge Graphs for Fact-aware Language Modeling","date":"2023-06-20","arxiv_id":"2306.11489","repositories_listed":0,"syntology":null},{"url":null,"slug":"lingua-manga-a-generic-large-language-model","title":"Lingua Manga: A Generic Large Language Model Centric System for Data Curation","date":"2023-06-20","arxiv_id":"2306.11702","repositories_listed":0,"syntology":null},{"url":null,"slug":"textbooks-are-all-you-need","title":"Textbooks Are All You Need","date":"2023-06-20","arxiv_id":"2306.11644","repositories_listed":0,"syntology":null},{"url":null,"slug":"jiuzhang-2-0-a-unified-chinese-pre-trained","title":"JiuZhang 2.0: A Unified Chinese Pre-trained Language Model for Multi-task Mathematical Problem Solving","date":"2023-06-19","arxiv_id":"2306.11027","repositories_listed":0,"syntology":null},{"url":null,"slug":"multilingual-few-shot-learning-via-language","title":"Multilingual Few-Shot Learning via Language Model Retrieval","date":"2023-06-19","arxiv_id":"2306.10964","repositories_listed":0,"syntology":null},{"url":null,"slug":"lm-vc-zero-shot-voice-conversion-via-speech","title":"LM-VC: Zero-shot Voice Conversion via Speech Generation based on Language Models","date":"2023-06-18","arxiv_id":"2306.10521","repositories_listed":0,"syntology":null},{"url":null,"slug":"ad-autogpt-an-autonomous-gpt-for-alzheimer-s","title":"AD-AutoGPT: An Autonomous GPT for Alzheimer's Disease Infodemiology","date":"2023-06-16","arxiv_id":"2306.10095","repositories_listed":0,"syntology":null},{"url":null,"slug":"clinicalgpt-large-language-models-finetuned","title":"ClinicalGPT: Large Language Models Finetuned with Diverse Medical Data and Comprehensive Evaluation","date":"2023-06-16","arxiv_id":"2306.09968","repositories_listed":0,"syntology":null},{"url":null,"slug":"cmlm-cse-based-on-conditional-mlm-contrastive","title":"CMLM-CSE: Based on Conditional MLM Contrastive Learning for Sentence Embeddings","date":"2023-06-16","arxiv_id":"2306.09594","repositories_listed":0,"syntology":null},{"url":null,"slug":"inspire-creativity-with-oriba-transform","title":"Inspire creativity with ORIBA: Transform Artists' Original Characters into Chatbots through Large Language Model","date":"2023-06-16","arxiv_id":"2306.09776","repositories_listed":0,"syntology":null},{"url":null,"slug":"investigating-masking-based-data-generation","title":"Investigating Masking-based Data Generation in Language Models","date":"2023-06-16","arxiv_id":"2307.00008","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-summarize-and-answer-questions","title":"Learning to Summarize and Answer Questions about a Virtual Robot's Past Actions","date":"2023-06-16","arxiv_id":"2306.09922","repositories_listed":0,"syntology":null},{"url":null,"slug":"process-knowledge-infused-learning-for-1","title":"Process Knowledge-infused Learning for Clinician-friendly Explanations","date":"2023-06-16","arxiv_id":"2306.09824","repositories_listed":0,"syntology":null},{"url":null,"slug":"block-state-transformer","title":"Block-State Transformers","date":"2023-06-15","arxiv_id":"2306.09539","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-chatgpt-pass-the-vietnamese-national-high","title":"Can ChatGPT pass the Vietnamese National High School Graduation Examination?","date":"2023-06-15","arxiv_id":"2306.09170","repositories_listed":0,"syntology":null},{"url":null,"slug":"distillation-strategies-for-discriminative","title":"Distillation Strategies for Discriminative Speech Recognition Rescoring","date":"2023-06-15","arxiv_id":"2306.09452","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-the-mit-mathematics-and-eecs","title":"Exploring the MIT Mathematics and EECS Curriculum Using Large Language Models","date":"2023-06-15","arxiv_id":"2306.08997","repositories_listed":0,"syntology":null},{"url":null,"slug":"mapping-researcher-activity-based-on","title":"Mapping Researcher Activity based on Publication Data by means of Transformers","date":"2023-06-15","arxiv_id":"2306.09049","repositories_listed":0,"syntology":null},{"url":null,"slug":"clipxplore-coupled-clip-and-shape-spaces-for","title":"CLIPXPlore: Coupled CLIP and Shape Spaces for 3D Shape Exploration","date":"2023-06-14","arxiv_id":"2306.08226","repositories_listed":0,"syntology":null},{"url":null,"slug":"radiology-gpt-a-large-language-model-for","title":"Radiology-GPT: A Large Language Model for Radiology","date":"2023-06-14","arxiv_id":"2306.08666","repositories_listed":0,"syntology":null},{"url":null,"slug":"recipes-for-sequential-pre-training-of","title":"Recipes for Sequential Pre-training of Multilingual Encoder and Seq2Seq Models","date":"2023-06-14","arxiv_id":"2306.08756","repositories_listed":0,"syntology":null},{"url":null,"slug":"avis-autonomous-visual-information-seeking","title":"AVIS: Autonomous Visual Information Seeking with Large Language Model Agent","date":"2023-06-13","arxiv_id":"2306.08129","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-scale-language-model-rescoring-on-long","title":"Large-scale Language Model Rescoring on Long-form Data","date":"2023-06-13","arxiv_id":"2306.08133","repositories_listed":0,"syntology":null},{"url":null,"slug":"pausespeech-natural-speech-synthesis-via-pre","title":"PauseSpeech: Natural Speech Synthesis via Pre-trained Language Model and Pause-based Prosody Modeling","date":"2023-06-13","arxiv_id":"2306.07489","repositories_listed":0,"syntology":null},{"url":null,"slug":"augmenting-language-models-with-long-term-1","title":"Augmenting Language Models with Long-Term Memory","date":"2023-06-12","arxiv_id":"2306.07174","repositories_listed":0,"syntology":null},{"url":null,"slug":"eriberta-a-bilingual-pre-trained-language","title":"EriBERTa: A Bilingual Pre-Trained Language Model for Clinical Natural Language Processing","date":"2023-06-12","arxiv_id":"2306.07373","repositories_listed":0,"syntology":null},{"url":null,"slug":"instructp2p-learning-to-edit-3d-point-clouds","title":"InstructP2P: Learning to Edit 3D Point Clouds with Text Instructions","date":"2023-06-12","arxiv_id":"2306.07154","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-models-and-non-linguistic","title":"Large language models and (non-)linguistic recursion","date":"2023-06-12","arxiv_id":"2306.07195","repositories_listed":0,"syntology":null},{"url":null,"slug":"weakly-supervised-information-extraction-from","title":"Weakly supervised information extraction from inscrutable handwritten document images","date":"2023-06-12","arxiv_id":"2306.06823","repositories_listed":0,"syntology":null},{"url":null,"slug":"robertweet-a-bert-language-model-for-romanian","title":"RoBERTweet: A BERT Language Model for Romanian Tweets","date":"2023-06-11","arxiv_id":"2306.06598","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-non-autoregressive-translation-1","title":"Improving Non-autoregressive Translation Quality with Pretrained Language Model, Embedding Distillation and Upsampling Strategy for CTC","date":"2023-06-10","arxiv_id":"2306.06345","repositories_listed":0,"syntology":null},{"url":null,"slug":"language-guided-traffic-simulation-via-scene","title":"Language-Guided Traffic Simulation via Scene-Level Diffusion","date":"2023-06-10","arxiv_id":"2306.06344","repositories_listed":0,"syntology":null},{"url":null,"slug":"s-3-increasing-gpu-utilization-during","title":"S$^{3}$: Increasing GPU Utilization during Generative Inference for Higher Throughput","date":"2023-06-09","arxiv_id":"2306.06000","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-a-robust-detection-of-language-model","title":"Towards a Robust Detection of Language Model Generated Text: Is ChatGPT that Easy to Detect?","date":"2023-06-09","arxiv_id":"2306.05871","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-language-model-integration-for","title":"Improving Language Model Integration for Neural Machine Translation","date":"2023-06-08","arxiv_id":"2306.05077","repositories_listed":0,"syntology":null},{"url":null,"slug":"infoprompt-information-theoretic-soft-prompt","title":"InfoPrompt: Information-Theoretic Soft Prompt Tuning for Natural Language Understanding","date":"2023-06-08","arxiv_id":"2306.04933","repositories_listed":0,"syntology":null},{"url":null,"slug":"mapping-brains-with-language-models-a-survey","title":"Mapping Brains with Language Models: A Survey","date":"2023-06-08","arxiv_id":"2306.05126","repositories_listed":0,"syntology":null},{"url":null,"slug":"speech-to-text-adapter-and-speech-to-entity","title":"Speech-to-Text Adapter and Speech-to-Entity Retriever Augmented LLMs for Speech Understanding","date":"2023-06-08","arxiv_id":"2306.07944","repositories_listed":0,"syntology":null},{"url":null,"slug":"absformer-transformer-based-model-for","title":"Absformer: Transformer-based Model for Unsupervised Multi-Document Abstractive Summarization","date":"2023-06-07","arxiv_id":"2306.04787","repositories_listed":0,"syntology":null},{"url":null,"slug":"benchmarking-foundation-models-with-language","title":"Benchmarking Foundation Models with Language-Model-as-an-Examiner","date":"2023-06-07","arxiv_id":"2306.04181","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluation-of-chatgpt-on-biomedical-tasks-a","title":"Evaluation of ChatGPT on Biomedical Tasks: A Zero-Shot Comparison with Fine-Tuned Generative Transformers","date":"2023-06-07","arxiv_id":"2306.04504","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-augmented-language-model-prompting","title":"Knowledge-Augmented Language Model Prompting for Zero-Shot Knowledge Graph Question Answering","date":"2023-06-07","arxiv_id":"2306.04136","repositories_listed":0,"syntology":null},{"url":null,"slug":"language-models-get-a-gender-makeover","title":"Language Models Get a Gender Makeover: Mitigating Gender Bias with Few-Shot Data Interventions","date":"2023-06-07","arxiv_id":"2306.04597","repositories_listed":0,"syntology":null},{"url":null,"slug":"long-form-analogies-generated-by-chatgpt-lack","title":"Long-form analogies generated by chatGPT lack human-like psycholinguistic properties","date":"2023-06-07","arxiv_id":"2306.04537","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-task-training-with-in-domain-language","title":"Multi-Task Training with In-Domain Language Models for Diagnostic Reasoning","date":"2023-06-07","arxiv_id":"2306.04551","repositories_listed":0,"syntology":null},{"url":null,"slug":"soft-prompt-tuning-for-large-language-models","title":"Soft-prompt Tuning for Large Language Models to Evaluate Bias","date":"2023-06-07","arxiv_id":"2306.04735","repositories_listed":0,"syntology":null},{"url":null,"slug":"text-only-domain-adaptation-using-unified","title":"Text-only Domain Adaptation using Unified Speech-Text Representation in Transducer","date":"2023-06-07","arxiv_id":"2306.04076","repositories_listed":0,"syntology":null},{"url":null,"slug":"transfer-learning-from-pre-trained-language","title":"Transfer Learning from Pre-trained Language Models Improves End-to-End Speech Summarization","date":"2023-06-07","arxiv_id":"2306.04233","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-generative-framework-for-conversational","title":"A generative framework for conversational laughter: Its 'language model' and laughter sound synthesis","date":"2023-06-06","arxiv_id":"2306.03465","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-assessment-of-oral-reading-accuracy","title":"Automatic Assessment of Oral Reading Accuracy for Reading Diagnostics","date":"2023-06-06","arxiv_id":"2306.03444","repositories_listed":0,"syntology":null},{"url":null,"slug":"iterative-translation-refinement-with-large","title":"Iterative Translation Refinement with Large Language Models","date":"2023-06-06","arxiv_id":"2306.03856","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-explicit-procedural-instructions","title":"Leveraging Explicit Procedural Instructions for Data-Efficient Action Prediction","date":"2023-06-06","arxiv_id":"2306.03959","repositories_listed":0,"syntology":null},{"url":null,"slug":"mega-tts-zero-shot-text-to-speech-at-scale","title":"Mega-TTS: Zero-Shot Text-to-Speech at Scale with Intrinsic Inductive Bias","date":"2023-06-06","arxiv_id":"2306.03509","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-scalable-and-adaptive-system-to-infer-the","title":"A Scalable and Adaptive System to Infer the Industry Sectors of Companies: Prompt + Model Tuning of Generative Language Models","date":"2023-06-05","arxiv_id":"2306.03313","repositories_listed":0,"syntology":null},{"url":"/paper/celda-leveraging-black-box-language-model-as","slug":"celda-leveraging-black-box-language-model-as","title":"CELDA: Leveraging Black-box Language Model as Enhanced Classifier without Labels","date":"2023-06-05","arxiv_id":"2306.02693","repositories_listed":0,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/celda-leveraging-black-box-language-model-as#ran","syntology_url":"https://syntology.ai/paper/2306.02693","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.02693"}},"official":null}},{"url":null,"slug":"cosines-contrastive-siamese-network-for","title":"CoSiNES: Contrastive Siamese Network for Entity Standardization","date":"2023-06-05","arxiv_id":"2306.03316","repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-lingual-transfer-learning-for-phrase","title":"Cross-Lingual Transfer Learning for Phrase Break Prediction with Multilingual Language Model","date":"2023-06-05","arxiv_id":"2306.02579","repositories_listed":0,"syntology":null},{"url":null,"slug":"ctrl-connect-tabular-and-language-model-for","title":"CTRL: Connect Collaborative and Language Model for CTR Prediction","date":"2023-06-05","arxiv_id":"2306.02841","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluation-of-ai-chatbots-for-patient","title":"Evaluation of AI Chatbots for Patient-Specific EHR Questions","date":"2023-06-05","arxiv_id":"2306.02549","repositories_listed":0,"syntology":null},{"url":null,"slug":"graph-aware-language-model-pre-training-on-a","title":"Graph-Aware Language Model Pre-Training on a Large Graph Corpus Can Help Multiple Graph Applications","date":"2023-06-05","arxiv_id":"2306.02592","repositories_listed":0,"syntology":null},{"url":null,"slug":"information-flow-control-in-machine-learning","title":"Information Flow Control in Machine Learning through Modular Model Architecture","date":"2023-06-05","arxiv_id":"2306.03235","repositories_listed":0,"syntology":null},{"url":null,"slug":"modeling-human-like-concept-learning-with","title":"Human-like Few-Shot Learning via Bayesian Reasoning over Natural Language","date":"2023-06-05","arxiv_id":"2306.02797","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-scientific-debt-in-nlp-a-case-for-more","title":"On \"Scientific Debt\" in NLP: A Case for More Rigour in Language Model Pre-Training Research","date":"2023-06-05","arxiv_id":"2306.02870","repositories_listed":0,"syntology":null},{"url":null,"slug":"polyvoice-language-models-for-speech-to","title":"PolyVoice: Language Models for Speech to Speech Translation","date":"2023-06-05","arxiv_id":"2306.02982","repositories_listed":0,"syntology":null},{"url":null,"slug":"visually-grounded-descriptions-improve-zero","title":"Semantically-Prompted Language Models Improve Visual Descriptions","date":"2023-06-05","arxiv_id":"2306.06077","repositories_listed":0,"syntology":null},{"url":null,"slug":"commonsense-knowledge-transfer-for-pre-1","title":"Commonsense Knowledge Transfer for Pre-trained Language Models","date":"2023-06-04","arxiv_id":"2306.02388","repositories_listed":0,"syntology":null},{"url":null,"slug":"radling-towards-efficient-radiology-report","title":"RadLing: Towards Efficient Radiology Report Understanding","date":"2023-06-04","arxiv_id":"2306.02492","repositories_listed":0,"syntology":null},{"url":null,"slug":"sen2pro-a-probabilistic-perspective-to","title":"Sen2Pro: A Probabilistic Perspective to Sentence Embedding from Pre-trained Language Model","date":"2023-06-04","arxiv_id":"2306.02247","repositories_listed":0,"syntology":null},{"url":null,"slug":"utilizing-chatgpt-to-enhance-clinical-trial","title":"Utilizing ChatGPT to Enhance Clinical Trial Enrollment","date":"2023-06-03","arxiv_id":"2306.02077","repositories_listed":0,"syntology":null}],"record_sha256":"70f71671142a9578c276f918fff8412c929e2d781c4abc69c70842b4fed37873","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}