{"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/t5/papers/3","list_of":"/method/t5","method":"T5","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":3,"pages_in_order":8,"rows_per_page":100,"rows":[201,300],"of":708,"counts":{"archive_papers_tagged":708,"with_a_code_link":353,"where_syntology_ran_a_sample":99,"not_listed_spam_title":0,"listed":708,"listed_where_code_ran":99,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":85,"every_run_a_failure_of_syntologys_instrument":14,"listed_with_a_run_with_no_instrument_failure":85,"listed_every_run_a_failure_of_syntologys_instrument":14,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/method/t5","prev":"/method/t5/papers/2","next":"/method/t5/papers/4","papers":[{"paper":"/paper/ast-t5-structure-aware-pretraining-for-code","slug":"ast-t5-structure-aware-pretraining-for-code","title":"AST-T5: Structure-Aware Pretraining for Code Generation and Understanding","date":"2024-01-05","arxiv_id":"2401.03003","n_code_links":1,"syntology":{"ran":5,"of":6,"n_ran_checked":5,"n_instrument":0,"unverified":1,"pointer_only":6,"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) · 1 unverified","official":{"repos":["gonglinyuan/ast_t5"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"are-llms-robust-for-spoken-dialogues","title":"Are LLMs Robust for Spoken Dialogues?","date":"2024-01-04","arxiv_id":"2401.02297","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-models-in-mental-health-care-a","title":"Large Language Models in Mental Health Care: a Scoping Review","date":"2024-01-01","arxiv_id":"2401.02984","n_code_links":0,"syntology":null},{"paper":"/paper/scaling-down-litting-up-efficient-zero-shot","slug":"scaling-down-litting-up-efficient-zero-shot","title":"Scaling Down, LiTting Up: Efficient Zero-Shot Listwise Reranking with Seq2seq Encoder-Decoder Models","date":"2023-12-26","arxiv_id":"2312.16098","n_code_links":2,"syntology":null},{"paper":"/paper/numerical-reasoning-for-financial-reports","slug":"numerical-reasoning-for-financial-reports","title":"Numerical Reasoning for Financial Reports","date":"2023-12-22","arxiv_id":"2312.14870","n_code_links":1,"syntology":null},{"paper":null,"slug":"theory-of-hallucinations-based-on","title":"Theory of Hallucinations based on Equivariance","date":"2023-12-22","arxiv_id":"2312.14504","n_code_links":0,"syntology":null},{"paper":null,"slug":"aspect-based-sentiment-analysis-with-explicit","title":"Aspect-Based Sentiment Analysis with Explicit Sentiment Augmentations","date":"2023-12-18","arxiv_id":"2312.10961","n_code_links":0,"syntology":null},{"paper":"/paper/multilingual-large-language-models-leak-human","slug":"multilingual-large-language-models-leak-human","title":"Multilingual large language models leak human stereotypes across language boundaries","date":"2023-12-12","arxiv_id":"2312.07141","n_code_links":1,"syntology":null},{"paper":null,"slug":"translating-natural-language-queries-to-sql","title":"Translating Natural Language Queries to SQL Using the T5 Model","date":"2023-12-12","arxiv_id":"2312.12414","n_code_links":0,"syntology":null},{"paper":null,"slug":"aikyam-a-video-conferencing-utility-for-deaf","title":"Aikyam: A Video Conferencing Utility for Deaf and Dumb","date":"2023-12-10","arxiv_id":"2312.05962","n_code_links":0,"syntology":null},{"paper":null,"slug":"domain-adaptation-of-a-state-of-the-art-text","title":"Domain Adaptation of a State of the Art Text-to-SQL Model: Lessons Learned and Challenges Found","date":"2023-12-09","arxiv_id":"2312.05448","n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-reinforcement-learning-and-large","title":"PerfRL: A Small Language Model Framework for Efficient Code Optimization","date":"2023-12-09","arxiv_id":"2312.05657","n_code_links":0,"syntology":null},{"paper":null,"slug":"converting-epics-stories-into-pseudocode","title":"Converting Epics/Stories into Pseudocode using Transformers","date":"2023-12-08","arxiv_id":"2312.05047","n_code_links":0,"syntology":null},{"paper":null,"slug":"making-translators-privacy-aware-on-the-user","title":"Making Translators Privacy-aware on the User's Side","date":"2023-12-07","arxiv_id":"2312.04068","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-text-to-text-model-for-multilingual","title":"A Text-to-Text Model for Multilingual Offensive Language Identification","date":"2023-12-06","arxiv_id":"2312.03379","n_code_links":0,"syntology":null},{"paper":null,"slug":"compositional-generalization-for-data-to-text","title":"Compositional Generalization for Data-to-Text Generation","date":"2023-12-05","arxiv_id":"2312.02748","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-machine-learning-approach-towards-skill","title":"A Machine Learning Approach Towards SKILL Code Autocompletion","date":"2023-12-04","arxiv_id":"2312.01921","n_code_links":0,"syntology":null},{"paper":"/paper/harnessing-the-power-of-prompt-based","slug":"harnessing-the-power-of-prompt-based","title":"Harnessing the Power of Prompt-based Techniques for Generating School-Level Questions using Large Language Models","date":"2023-12-02","arxiv_id":"2312.01032","n_code_links":1,"syntology":null},{"paper":null,"slug":"towards-leveraging-llms-for-conditional-qa","title":"Towards leveraging LLMs for Conditional QA","date":"2023-12-02","arxiv_id":"2312.01143","n_code_links":0,"syntology":null},{"paper":"/paper/data-generation-for-post-ocr-correction-of","slug":"data-generation-for-post-ocr-correction-of","title":"Data Generation for Post-OCR correction of Cyrillic handwriting","date":"2023-11-27","arxiv_id":"2311.15896","n_code_links":2,"syntology":null},{"paper":"/paper/image-super-resolution-with-text-prompt","slug":"image-super-resolution-with-text-prompt","title":"Image Super-Resolution with Text Prompt Diffusion","date":"2023-11-24","arxiv_id":"2311.14282","n_code_links":1,"syntology":null},{"paper":"/paper/compeft-compression-for-communicating","slug":"compeft-compression-for-communicating","title":"ComPEFT: Compression for Communicating Parameter Efficient Updates via Sparsification and Quantization","date":"2023-11-22","arxiv_id":"2311.13171","n_code_links":1,"syntology":{"ran":8,"of":10,"n_ran_checked":7,"n_instrument":1,"unverified":2,"pointer_only":1,"phrase":"8 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; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["prateeky2806/compeft"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"bit-cipher-a-simple-yet-powerful-word","title":"Bit Cipher -- A Simple yet Powerful Word Representation System that Integrates Efficiently with Language Models","date":"2023-11-18","arxiv_id":"2311.11012","n_code_links":0,"syntology":null},{"paper":"/paper/vashantor-a-large-scale-multilingual","slug":"vashantor-a-large-scale-multilingual","title":"Vashantor: A Large-scale Multilingual Benchmark Dataset for Automated Translation of Bangla Regional Dialects to Bangla Language","date":"2023-11-18","arxiv_id":"2311.11142","n_code_links":1,"syntology":null},{"paper":"/paper/dynapipe-optimizing-multi-task-training","slug":"dynapipe-optimizing-multi-task-training","title":"DynaPipe: Optimizing Multi-task Training through Dynamic Pipelines","date":"2023-11-17","arxiv_id":"2311.10418","n_code_links":2,"syntology":null},{"paper":null,"slug":"memory-augmented-language-models-through","title":"Memory Augmented Language Models through Mixture of Word Experts","date":"2023-11-15","arxiv_id":"2311.10768","n_code_links":0,"syntology":null},{"paper":"/paper/spot-a-natural-language-interface-for","slug":"spot-a-natural-language-interface-for","title":"Spot: A Natural Language Interface for Geospatial Searches in OSM","date":"2023-11-14","arxiv_id":"2311.08093","n_code_links":1,"syntology":null},{"paper":null,"slug":"ut5-pretraining-non-autoregressive-t5-with","title":"UT5: Pretraining Non autoregressive T5 with unrolled denoising","date":"2023-11-14","arxiv_id":"2311.08552","n_code_links":0,"syntology":null},{"paper":null,"slug":"controllable-topic-focused-abstractive","title":"Controllable Topic-Focused Abstractive Summarization","date":"2023-11-12","arxiv_id":"2311.06724","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-fine-tuning-chatgpt-for-news","title":"Exploring Fine-tuning ChatGPT for News Recommendation","date":"2023-11-10","arxiv_id":"2311.05850","n_code_links":0,"syntology":null},{"paper":"/paper/deep-learning-brasil-at-absapt-2022","slug":"deep-learning-brasil-at-absapt-2022","title":"Deep Learning Brasil at ABSAPT 2022: Portuguese Transformer Ensemble Approaches","date":"2023-11-08","arxiv_id":"2311.05051","n_code_links":1,"syntology":null},{"paper":null,"slug":"adapting-pre-trained-generative-models-for","title":"Adapting Pre-trained Generative Models for Extractive Question Answering","date":"2023-11-06","arxiv_id":"2311.02961","n_code_links":0,"syntology":null},{"paper":"/paper/famesumm-investigating-and-improving","slug":"famesumm-investigating-and-improving","title":"FaMeSumm: Investigating and Improving Faithfulness of Medical Summarization","date":"2023-11-03","arxiv_id":"2311.02271","n_code_links":1,"syntology":{"ran":3,"of":6,"n_ran_checked":3,"n_instrument":0,"unverified":3,"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) · 3 unverified","official":{"repos":["psunlpgroup/famesumm"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/indo-lego-absa-a-multitask-generative-aspect","slug":"indo-lego-absa-a-multitask-generative-aspect","title":"Indo LEGO-ABSA: A Multitask Generative Aspect Based Sentiment Analysis for Indonesian Language","date":"2023-11-03","arxiv_id":"2311.01757","n_code_links":1,"syntology":null},{"paper":"/paper/better-together-enhancing-generative","slug":"better-together-enhancing-generative","title":"Better Together: Enhancing Generative Knowledge Graph Completion with Language Models and Neighborhood Information","date":"2023-11-02","arxiv_id":"2311.01326","n_code_links":1,"syntology":null},{"paper":null,"slug":"learning-defect-prediction-from-unrealistic","title":"Learning Defect Prediction from Unrealistic Data","date":"2023-11-02","arxiv_id":"2311.00931","n_code_links":0,"syntology":null},{"paper":null,"slug":"maaig-motion-analysis-and-instruction","title":"MAAIG: Motion Analysis And Instruction Generation","date":"2023-11-02","arxiv_id":"2311.00980","n_code_links":0,"syntology":null},{"paper":null,"slug":"attention-alignment-and-flexible-positional","title":"Attention Alignment and Flexible Positional Embeddings Improve Transformer Length Extrapolation","date":"2023-11-01","arxiv_id":"2311.00684","n_code_links":0,"syntology":null},{"paper":"/paper/data-augmentation-for-code-translation-with","slug":"data-augmentation-for-code-translation-with","title":"Data Augmentation for Code Translation with Comparable Corpora and Multiple References","date":"2023-11-01","arxiv_id":"2311.00317","n_code_links":1,"syntology":{"ran":6,"of":12,"n_ran_checked":6,"n_instrument":0,"unverified":6,"pointer_only":12,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified","official":{"repos":["veronicium/cmtrans"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":"/paper/generating-medical-instructions-with","slug":"generating-medical-instructions-with","title":"Generating Medical Prescriptions with Conditional Transformer","date":"2023-10-30","arxiv_id":"2310.19727","n_code_links":1,"syntology":{"ran":10,"of":14,"n_ran_checked":7,"n_instrument":3,"unverified":4,"pointer_only":14,"phrase":"10 ran (of which 4 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified","official":{"repos":["hecta-uom/label-to-text-transformer"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":4,"n_ran_no_instrument_failure":7,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/lightlm-a-lightweight-deep-and-narrow","slug":"lightlm-a-lightweight-deep-and-narrow","title":"LightLM: A Lightweight Deep and Narrow Language Model for Generative Recommendation","date":"2023-10-26","arxiv_id":"2310.17488","n_code_links":1,"syntology":{"ran":11,"of":12,"n_ran_checked":11,"n_instrument":0,"unverified":1,"pointer_only":12,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 1 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["dongyuanjushi/lightlm"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/redco-a-lightweight-tool-to-automate","slug":"redco-a-lightweight-tool-to-automate","title":"RedCoast: A Lightweight Tool to Automate Distributed Training of LLMs on Any GPU/TPUs","date":"2023-10-25","arxiv_id":"2310.16355","n_code_links":1,"syntology":{"ran":12,"of":17,"n_ran_checked":12,"n_instrument":0,"unverified":5,"pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","official":{"repos":["tanyuqian/redco"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"efficient-data-learning-for-open-information","title":"Efficient Data Learning for Open Information Extraction with Pre-trained Language Models","date":"2023-10-23","arxiv_id":"2310.15021","n_code_links":0,"syntology":null},{"paper":"/paper/once-upon-a-textit-time-in-textit-graph","slug":"once-upon-a-textit-time-in-textit-graph","title":"Once Upon a $\\textit{Time}$ in $\\textit{Graph}$: Relative-Time Pretraining for Complex Temporal Reasoning","date":"2023-10-23","arxiv_id":"2310.14709","n_code_links":1,"syntology":{"ran":7,"of":11,"n_ran_checked":7,"n_instrument":0,"unverified":4,"pointer_only":2,"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":["damo-nlp-sg/rememo"],"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/improving-cross-lingual-transfer-through","slug":"improving-cross-lingual-transfer-through","title":"Improving Cross-Lingual Transfer through Subtree-Aware Word Reordering","date":"2023-10-20","arxiv_id":"2310.13583","n_code_links":1,"syntology":null},{"paper":null,"slug":"empirical-study-of-pretrained-multilingual","title":"Empirical study of pretrained multilingual language models for zero-shot cross-lingual knowledge transfer in generation","date":"2023-10-15","arxiv_id":"2310.09917","n_code_links":0,"syntology":null},{"paper":"/paper/retrieval-generation-alignment-for-end-to-end","slug":"retrieval-generation-alignment-for-end-to-end","title":"Retrieval-Generation Alignment for End-to-End Task-Oriented Dialogue System","date":"2023-10-13","arxiv_id":"2310.08877","n_code_links":1,"syntology":null},{"paper":null,"slug":"answer-candidate-type-selection-text-to-text","title":"Answer Candidate Type Selection: Text-to-Text Language Model for Closed Book Question Answering Meets Knowledge Graphs","date":"2023-10-10","arxiv_id":"2310.07008","n_code_links":0,"syntology":null},{"paper":"/paper/sparse-finetuning-for-inference-acceleration","slug":"sparse-finetuning-for-inference-acceleration","title":"Sparse Fine-tuning for Inference Acceleration of Large Language Models","date":"2023-10-10","arxiv_id":"2310.06927","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["ist-daslab/sparsefinetuning"],"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":"automating-customer-service-using-langchain","title":"Automating Customer Service using LangChain: Building custom open-source GPT Chatbot for organizations","date":"2023-10-09","arxiv_id":"2310.05421","n_code_links":0,"syntology":null},{"paper":null,"slug":"benchmarking-large-language-models-with","title":"Benchmarking Large Language Models with Augmented Instructions for Fine-grained Information Extraction","date":"2023-10-08","arxiv_id":"2310.05092","n_code_links":0,"syntology":null},{"paper":"/paper/slogan-generation-with-noise-perturbation","slug":"slogan-generation-with-noise-perturbation","title":"Effective Slogan Generation with Noise Perturbation","date":"2023-10-06","arxiv_id":"2310.04472","n_code_links":1,"syntology":null},{"paper":"/paper/can-large-language-models-be-good-path","slug":"can-large-language-models-be-good-path","title":"Can Large Language Models be Good Path Planners? A Benchmark and Investigation on Spatial-temporal Reasoning","date":"2023-10-05","arxiv_id":"2310.03249","n_code_links":1,"syntology":{"ran":28,"of":28,"n_ran_checked":28,"n_instrument":0,"unverified":0,"pointer_only":28,"phrase":"28 ran (of which 0 constructed an object rather than computing a result; 28 with no instrument failure: 0 honoured, 0 violated, 28 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["mohamedaghzal/llms-as-path-planners"],"state":"official (archive's flag): 28 ran","n_ran":28,"n_constructed":0,"n_ran_no_instrument_failure":28,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/dspy-compiling-declarative-language-model","slug":"dspy-compiling-declarative-language-model","title":"DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines","date":"2023-10-05","arxiv_id":"2310.03714","n_code_links":3,"syntology":{"ran":3,"of":7,"n_ran_checked":3,"n_instrument":0,"unverified":4,"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) · 4 unverified","official":{"repos":["stanfordnlp/dspy"],"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":"natural-language-models-for-data","title":"Natural Language Models for Data Visualization Utilizing nvBench Dataset","date":"2023-10-02","arxiv_id":"2310.00832","n_code_links":0,"syntology":null},{"paper":null,"slug":"testing-the-limits-of-unified-sequence-to","title":"Testing the Limits of Unified Sequence to Sequence LLM Pretraining on Diverse Table Data Tasks","date":"2023-10-01","arxiv_id":"2310.00789","n_code_links":0,"syntology":null},{"paper":"/paper/capp-130-a-corpus-of-chinese-application","slug":"capp-130-a-corpus-of-chinese-application","title":"CAPP-130: A Corpus of Chinese Application Privacy Policy Summarization and Interpretation","date":"2023-09-26","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"program-repair-with-minimal-edits-using","title":"Program Repair with Minimal Edits Using CodeT5","date":"2023-09-26","arxiv_id":"2309.14760","n_code_links":0,"syntology":null},{"paper":"/paper/on-the-relationship-between-skill-neurons-and","slug":"on-the-relationship-between-skill-neurons-and","title":"On the Relationship between Skill Neurons and Robustness in Prompt Tuning","date":"2023-09-21","arxiv_id":"2309.12263","n_code_links":1,"syntology":null},{"paper":null,"slug":"localize-retrieve-and-fuse-a-generalized","title":"Localize, Retrieve and Fuse: A Generalized Framework for Free-Form Question Answering over Tables","date":"2023-09-20","arxiv_id":"2309.11049","n_code_links":0,"syntology":null},{"paper":"/paper/sequence-to-sequence-spanish-pre-trained","slug":"sequence-to-sequence-spanish-pre-trained","title":"Sequence-to-Sequence Spanish Pre-trained Language Models","date":"2023-09-20","arxiv_id":"2309.11259","n_code_links":1,"syntology":null},{"paper":null,"slug":"accelerating-in-browser-deep-learning","title":"Empowering In-Browser Deep Learning Inference on Edge Devices with Just-in-Time Kernel Optimizations","date":"2023-09-16","arxiv_id":"2309.08978","n_code_links":0,"syntology":null},{"paper":"/paper/structural-self-supervised-objectives-for","slug":"structural-self-supervised-objectives-for","title":"Structural Self-Supervised Objectives for Transformers","date":"2023-09-15","arxiv_id":"2309.08272","n_code_links":1,"syntology":null},{"paper":"/paper/dblplink-an-entity-linker-for-the-dblp","slug":"dblplink-an-entity-linker-for-the-dblp","title":"DBLPLink: An Entity Linker for the DBLP Scholarly Knowledge Graph","date":"2023-09-14","arxiv_id":"2309.07545","n_code_links":1,"syntology":null},{"paper":"/paper/benchmarking-procedural-language","slug":"benchmarking-procedural-language","title":"Benchmarking Procedural Language Understanding for Low-Resource Languages: A Case Study on Turkish","date":"2023-09-13","arxiv_id":"2309.06698","n_code_links":1,"syntology":null},{"paper":null,"slug":"2309-06057","title":"RAP-Gen: Retrieval-Augmented Patch Generation with CodeT5 for Automatic Program Repair","date":"2023-09-12","arxiv_id":"2309.06057","n_code_links":0,"syntology":null},{"paper":null,"slug":"detecting-natural-language-biases-with-prompt","title":"Detecting Natural Language Biases with Prompt-based Learning","date":"2023-09-11","arxiv_id":"2309.05227","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-nlp-models-identify-distinguish-and","title":"Can NLP Models 'Identify', 'Distinguish', and 'Justify' Questions that Don't have a Definitive Answer?","date":"2023-09-08","arxiv_id":"2309.04635","n_code_links":0,"syntology":null},{"paper":"/paper/nanot5-a-pytorch-framework-for-pre-training","slug":"nanot5-a-pytorch-framework-for-pre-training","title":"nanoT5: A PyTorch Framework for Pre-training and Fine-tuning T5-style Models with Limited Resources","date":"2023-09-05","arxiv_id":"2309.02373","n_code_links":1,"syntology":{"ran":6,"of":9,"n_ran_checked":6,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["piotrnawrot/nanot5"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/transformer-compression-via-subspace","slug":"transformer-compression-via-subspace","title":"$\\rm SP^3$: Enhancing Structured Pruning via PCA Projection","date":"2023-08-31","arxiv_id":"2308.16475","n_code_links":1,"syntology":{"ran":12,"of":14,"n_ran_checked":11,"n_instrument":1,"unverified":2,"pointer_only":14,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 1 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["hyx1999/sp3"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/multi-party-goal-tracking-with-llms-comparing","slug":"multi-party-goal-tracking-with-llms-comparing","title":"Multi-party Goal Tracking with LLMs: Comparing Pre-training, Fine-tuning, and Prompt Engineering","date":"2023-08-29","arxiv_id":"2308.15231","n_code_links":1,"syntology":null},{"paper":"/paper/fire-food-image-to-recipe-generation","slug":"fire-food-image-to-recipe-generation","title":"FIRE: Food Image to REcipe generation","date":"2023-08-28","arxiv_id":"2308.14391","n_code_links":1,"syntology":{"ran":12,"of":16,"n_ran_checked":10,"n_instrument":2,"unverified":4,"pointer_only":16,"phrase":"12 ran (of which 2 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","official":{"repos":["prateekchhikara/fire"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":2,"n_ran_no_instrument_failure":10,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/unipt-universal-parallel-tuning-for-transfer","slug":"unipt-universal-parallel-tuning-for-transfer","title":"UniPT: Universal Parallel Tuning for Transfer Learning with Efficient Parameter and Memory","date":"2023-08-28","arxiv_id":"2308.14316","n_code_links":1,"syntology":null},{"paper":null,"slug":"improving-knowledge-distillation-for-bert","title":"Improving Knowledge Distillation for BERT Models: Loss Functions, Mapping Methods, and Weight Tuning","date":"2023-08-26","arxiv_id":"2308.13958","n_code_links":0,"syntology":null},{"paper":null,"slug":"mitigating-the-exposure-bias-in-sentence","title":"Mitigating the Exposure Bias in Sentence-Level Grapheme-to-Phoneme (G2P) Transduction","date":"2023-08-16","arxiv_id":"2308.08442","n_code_links":0,"syntology":null},{"paper":null,"slug":"automated-test-case-generation-using-code","title":"Domain Adaptation for Code Model-based Unit Test Case Generation","date":"2023-08-15","arxiv_id":"2308.08033","n_code_links":0,"syntology":null},{"paper":null,"slug":"beware-of-deception-detecting-half-truth-and","title":"\"Beware of deception\": Detecting Half-Truth and Debunking it through Controlled Claim Editing","date":"2023-08-15","arxiv_id":"2308.07973","n_code_links":0,"syntology":null},{"paper":"/paper/easyedit-an-easy-to-use-knowledge-editing","slug":"easyedit-an-easy-to-use-knowledge-editing","title":"EasyEdit: An Easy-to-use Knowledge Editing Framework for Large Language Models","date":"2023-08-14","arxiv_id":"2308.07269","n_code_links":2,"syntology":{"ran":4,"of":6,"n_ran_checked":3,"n_instrument":1,"unverified":2,"pointer_only":0,"phrase":"4 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; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["zjunlp/easyedit","zjunlp/knowlm"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"thinking-like-an-expert-multimodal-hypergraph","title":"Thinking Like an Expert:Multimodal Hypergraph-of-Thought (HoT) Reasoning to boost Foundation Modals","date":"2023-08-11","arxiv_id":"2308.06207","n_code_links":0,"syntology":null},{"paper":"/paper/you-only-prompt-once-on-the-capabilities-of","slug":"you-only-prompt-once-on-the-capabilities-of","title":"You Only Prompt Once: On the Capabilities of Prompt Learning on Large Language Models to Tackle Toxic Content","date":"2023-08-10","arxiv_id":"2308.05596","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: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["xinleihe/toxic-prompt"],"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":"lora-fa-memory-efficient-low-rank-adaptation","title":"LoRA-FA: Memory-efficient Low-rank Adaptation for Large Language Models Fine-tuning","date":"2023-08-07","arxiv_id":"2308.03303","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-controllable-natural-language","title":"Towards Controllable Natural Language Inference through Lexical Inference Types","date":"2023-08-07","arxiv_id":"2308.03581","n_code_links":0,"syntology":null},{"paper":"/paper/instructed-to-bias-instruction-tuned-language","slug":"instructed-to-bias-instruction-tuned-language","title":"Instructed to Bias: Instruction-Tuned Language Models Exhibit Emergent Cognitive Bias","date":"2023-08-01","arxiv_id":"2308.00225","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"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) · 0 unverified","official":{"repos":["itay1itzhak/instructedtobias"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/no-that-s-not-what-i-meant-handling-third","slug":"no-that-s-not-what-i-meant-handling-third","title":"No that's not what I meant: Handling Third Position Repair in Conversational Question Answering","date":"2023-07-31","arxiv_id":"2307.16689","n_code_links":1,"syntology":null},{"paper":"/paper/evaluating-generative-models-for-graph-to","slug":"evaluating-generative-models-for-graph-to","title":"Evaluating Generative Models for Graph-to-Text Generation","date":"2023-07-27","arxiv_id":"2307.14712","n_code_links":1,"syntology":null},{"paper":null,"slug":"speed-reading-tool-powered-by-artificial","title":"Speed Reading Tool Powered by Artificial Intelligence for Students with ADHD, Dyslexia, or Short Attention Span","date":"2023-07-26","arxiv_id":"2307.14544","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-end-to-end-workflow-using-topic","title":"An End-to-End Workflow using Topic Segmentation and Text Summarisation Methods for Improved Podcast Comprehension","date":"2023-07-25","arxiv_id":"2307.13394","n_code_links":0,"syntology":null},{"paper":null,"slug":"generating-mathematical-derivations-with","title":"Controlling Equational Reasoning in Large Language Models with Prompt Interventions","date":"2023-07-19","arxiv_id":"2307.09998","n_code_links":0,"syntology":null},{"paper":null,"slug":"emotionprompt-leveraging-psychology-for-large","title":"Large Language Models Understand and Can be Enhanced by Emotional Stimuli","date":"2023-07-14","arxiv_id":"2307.11760","n_code_links":0,"syntology":null},{"paper":null,"slug":"agreement-tracking-for-multi-issue","title":"Agreement Tracking for Multi-Issue Negotiation Dialogues","date":"2023-07-13","arxiv_id":"2307.06524","n_code_links":0,"syntology":null},{"paper":"/paper/no-train-no-gain-revisiting-efficient","slug":"no-train-no-gain-revisiting-efficient","title":"No Train No Gain: Revisiting Efficient Training Algorithms For Transformer-based Language Models","date":"2023-07-12","arxiv_id":"2307.06440","n_code_links":1,"syntology":{"ran":10,"of":13,"n_ran_checked":10,"n_instrument":0,"unverified":3,"pointer_only":13,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 3 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["jeankaddour/notrainnogain"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["official","unlocated"]}}},{"paper":null,"slug":"text-simplification-of-scientific-texts-for","title":"Text Simplification of Scientific Texts for Non-Expert Readers","date":"2023-07-07","arxiv_id":"2307.03569","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-continual-learning-for-code","title":"Exploring Continual Learning for Code Generation Models","date":"2023-07-05","arxiv_id":"2307.02435","n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-denoised-abstract-meaning","title":"Leveraging Denoised Abstract Meaning Representation for Grammatical Error Correction","date":"2023-07-05","arxiv_id":"2307.02127","n_code_links":0,"syntology":null},{"paper":"/paper/multilingual-controllable-transformer-based","slug":"multilingual-controllable-transformer-based","title":"Multilingual Controllable Transformer-Based Lexical Simplification","date":"2023-07-05","arxiv_id":"2307.02120","n_code_links":1,"syntology":null},{"paper":null,"slug":"interpretability-and-transparency-driven","title":"Interpretability and Transparency-Driven Detection and Transformation of Textual Adversarial Examples (IT-DT)","date":"2023-07-03","arxiv_id":"2307.01225","n_code_links":0,"syntology":null},{"paper":"/paper/how-far-is-language-model-from-100-few-shot","slug":"how-far-is-language-model-from-100-few-shot","title":"How far is Language Model from 100% Few-shot Named Entity Recognition in Medical Domain","date":"2023-07-01","arxiv_id":"2307.00186","n_code_links":1,"syntology":null},{"paper":null,"slug":"abstractive-text-summarization-for-resumes","title":"Abstractive Text Summarization for Resumes With Cutting Edge NLP Transformers and LSTM","date":"2023-06-23","arxiv_id":"2306.13315","n_code_links":0,"syntology":null},{"paper":null,"slug":"gkd-generalized-knowledge-distillation-for","title":"On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes","date":"2023-06-23","arxiv_id":"2306.13649","n_code_links":0,"syntology":null},{"paper":"/paper/incorporating-graph-information-in","slug":"incorporating-graph-information-in","title":"Incorporating Graph Information in Transformer-based AMR Parsing","date":"2023-06-23","arxiv_id":"2306.13467","n_code_links":1,"syntology":null}],"record_sha256":"5d9ecd17999dfb1d64380c8cdfa251b6a45600bd99dcec0b1b742846428ce5c0","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}