{"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/sentencepiece/papers/4","list_of":"/method/sentencepiece","method":"SentencePiece","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"date (newest first), then slug","page":4,"pages_in_order":10,"rows_per_page":100,"rows":[301,400],"of":908,"counts":{"archive_papers_tagged":908,"with_a_code_link":438,"where_syntology_ran_a_sample":111,"not_listed_spam_title":0,"listed":908,"listed_where_code_ran":111,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":96,"every_run_a_failure_of_syntologys_instrument":15,"listed_with_a_run_with_no_instrument_failure":96,"listed_every_run_a_failure_of_syntologys_instrument":15,"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/sentencepiece","prev":"/method/sentencepiece/papers/3","next":"/method/sentencepiece/papers/5","papers":[{"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":"simple-is-better-and-large-is-not-enough","title":"Simple is Better and Large is Not Enough: Towards Ensembling of Foundational Language Models","date":"2023-08-23","arxiv_id":"2308.12272","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":null,"slug":"selfseg-a-self-supervised-sub-word","title":"SelfSeg: A Self-supervised Sub-word Segmentation Method for Neural Machine Translation","date":"2023-07-31","arxiv_id":"2307.16400","n_code_links":0,"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":"a-hybrid-machine-learning-model-for","title":"A Hybrid Machine Learning Model for Classifying Gene Mutations in Cancer using LSTM, BiLSTM, CNN, GRU, and GloVe","date":"2023-07-24","arxiv_id":"2307.14361","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},{"paper":null,"slug":"resume-information-extraction-via-post-ocr","title":"Resume Information Extraction via Post-OCR Text Processing","date":"2023-06-23","arxiv_id":"2306.13775","n_code_links":0,"syntology":null},{"paper":null,"slug":"investigating-pre-trained-language-models-on","title":"Investigating Pre-trained Language Models on Cross-Domain Datasets, a Step Closer to General AI","date":"2023-06-21","arxiv_id":"2306.12205","n_code_links":0,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-fusion-efficient-network-training-via","title":"Deep Fusion: Efficient Network Training via Pre-trained Initializations","date":"2023-06-20","arxiv_id":"2306.11903","n_code_links":0,"syntology":null},{"paper":"/paper/fine-tuning-language-models-for-scientific","slug":"fine-tuning-language-models-for-scientific","title":"Fine-Tuning Language Models for Scientific Writing Support","date":"2023-06-19","arxiv_id":"2306.10974","n_code_links":1,"syntology":null},{"paper":null,"slug":"summarization-from-leaderboards-to-practice","title":"Summarization from Leaderboards to Practice: Choosing A Representation Backbone and Ensuring Robustness","date":"2023-06-18","arxiv_id":"2306.10555","n_code_links":0,"syntology":null},{"paper":null,"slug":"research-on-named-entity-recognition-in","title":"Research on Named Entity Recognition in Improved transformer with R-Drop structure","date":"2023-06-14","arxiv_id":"2306.08315","n_code_links":0,"syntology":null},{"paper":null,"slug":"better-generalization-with-semantic-ids-a","title":"Better Generalization with Semantic IDs: A Case Study in Ranking for Recommendations","date":"2023-06-13","arxiv_id":"2306.08121","n_code_links":0,"syntology":null},{"paper":"/paper/unipoll-a-unified-social-media-poll","slug":"unipoll-a-unified-social-media-poll","title":"UniPoll: A Unified Social Media Poll Generation Framework via Multi-Objective Optimization","date":"2023-06-12","arxiv_id":"2306.06851","n_code_links":1,"syntology":null},{"paper":"/paper/attention-compilation-and-solver-based","slug":"attention-compilation-and-solver-based","title":"CoTran: An LLM-based Code Translator using Reinforcement Learning with Feedback from Compiler and Symbolic Execution","date":"2023-06-11","arxiv_id":"2306.06755","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-unified-generative-approach-to-product","title":"A Unified Generative Approach to Product Attribute-Value Identification","date":"2023-06-09","arxiv_id":"2306.05605","n_code_links":0,"syntology":null},{"paper":null,"slug":"triggering-multi-hop-reasoning-for-question","title":"Triggering Multi-Hop Reasoning for Question Answering in Language Models using Soft Prompts and Random Walks","date":"2023-06-06","arxiv_id":"2306.04009","n_code_links":0,"syntology":null},{"paper":"/paper/detector-guidance-for-multi-object-text-to","slug":"detector-guidance-for-multi-object-text-to","title":"Detector Guidance for Multi-Object Text-to-Image Generation","date":"2023-06-04","arxiv_id":"2306.02236","n_code_links":1,"syntology":null},{"paper":null,"slug":"modular-transformers-compressing-transformers","title":"Modular Transformers: Compressing Transformers into Modularized Layers for Flexible Efficient Inference","date":"2023-06-04","arxiv_id":"2306.02379","n_code_links":0,"syntology":null},{"paper":null,"slug":"5ider-unified-query-rewriting-for-steering","title":"5IDER: Unified Query Rewriting for Steering, Intent Carryover, Disfluencies, Entity Carryover and Repair","date":"2023-06-02","arxiv_id":"2306.01855","n_code_links":0,"syntology":null},{"paper":"/paper/adapting-pre-trained-language-models-to","slug":"adapting-pre-trained-language-models-to","title":"Adapting Pre-trained Language Models to Vision-Language Tasks via Dynamic Visual Prompting","date":"2023-06-01","arxiv_id":"2306.00409","n_code_links":1,"syntology":null},{"paper":null,"slug":"prequant-a-task-agnostic-quantization","title":"PreQuant: A Task-agnostic Quantization Approach for Pre-trained Language Models","date":"2023-05-30","arxiv_id":"2306.00014","n_code_links":0,"syntology":null},{"paper":null,"slug":"coeditor-leveraging-contextual-changes-for","title":"Coeditor: Leveraging Contextual Changes for Multi-round Code Auto-editing","date":"2023-05-29","arxiv_id":"2305.18584","n_code_links":0,"syntology":null},{"paper":"/paper/how-effective-are-neural-networks-for-fixing","slug":"how-effective-are-neural-networks-for-fixing","title":"How Effective Are Neural Networks for Fixing Security Vulnerabilities","date":"2023-05-29","arxiv_id":"2305.18607","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":0,"n_instrument":4,"unverified":0,"pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","official":{"repos":["lin-tan/llm-vul"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/knowledge-augmented-reasoning-distillation-1","slug":"knowledge-augmented-reasoning-distillation-1","title":"Knowledge-Augmented Reasoning Distillation for Small Language Models in Knowledge-Intensive Tasks","date":"2023-05-28","arxiv_id":"2305.18395","n_code_links":1,"syntology":{"ran":5,"of":6,"n_ran_checked":3,"n_instrument":2,"unverified":1,"pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["nardien/kard"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/towards-explainable-conversational","slug":"towards-explainable-conversational","title":"Towards Explainable Conversational Recommender Systems","date":"2023-05-27","arxiv_id":"2305.18363","n_code_links":1,"syntology":null},{"paper":"/paper/beyond-chain-of-thought-effective-graph-of","slug":"beyond-chain-of-thought-effective-graph-of","title":"Beyond Chain-of-Thought, Effective Graph-of-Thought Reasoning in Language Models","date":"2023-05-26","arxiv_id":"2305.16582","n_code_links":2,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["zoeyyao27/graph-of-thought"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/learning-to-imagine-visually-augmented","slug":"learning-to-imagine-visually-augmented","title":"Learning to Imagine: Visually-Augmented Natural Language Generation","date":"2023-05-26","arxiv_id":"2305.16944","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["rucaibox/live"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text"]}}},{"paper":"/paper/pre-training-meets-clustering-a-hybrid","slug":"pre-training-meets-clustering-a-hybrid","title":"Pre-training Meets Clustering: A Hybrid Extractive Multi-document Summarization Model","date":"2023-05-25","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"neural-summarization-of-electronic-health","title":"Neural Summarization of Electronic Health Records","date":"2023-05-24","arxiv_id":"2305.15222","n_code_links":0,"syntology":null},{"paper":"/paper/segmented-recurrent-transformer-an-efficient","slug":"segmented-recurrent-transformer-an-efficient","title":"Segmented Recurrent Transformer: An Efficient Sequence-to-Sequence Model","date":"2023-05-24","arxiv_id":"2305.16340","n_code_links":1,"syntology":null},{"paper":"/paper/compoundpiece-evaluating-and-improving","slug":"compoundpiece-evaluating-and-improving","title":"CompoundPiece: Evaluating and Improving Decompounding Performance of Language Models","date":"2023-05-23","arxiv_id":"2305.14214","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":3,"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":["bminixhofer/compoundpiece"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/exploring-large-language-models-for-classical","slug":"exploring-large-language-models-for-classical","title":"Exploring Large Language Models for Classical Philology","date":"2023-05-23","arxiv_id":"2305.13698","n_code_links":1,"syntology":null},{"paper":null,"slug":"grace-generation-using-associated-code-edits","title":"GrACE: Generation using Associated Code Edits","date":"2023-05-23","arxiv_id":"2305.14129","n_code_links":0,"syntology":null},{"paper":null,"slug":"mmt5-modular-multilingual-pre-training-solves","title":"mmT5: Modular Multilingual Pre-Training Solves Source Language Hallucinations","date":"2023-05-23","arxiv_id":"2305.14224","n_code_links":0,"syntology":null},{"paper":null,"slug":"nail-lexical-retrieval-indices-with-efficient","title":"NAIL: Lexical Retrieval Indices with Efficient Non-Autoregressive Decoders","date":"2023-05-23","arxiv_id":"2305.14499","n_code_links":0,"syntology":null},{"paper":"/paper/on-robustness-of-finetuned-transformer-based","slug":"on-robustness-of-finetuned-transformer-based","title":"On Robustness of Finetuned Transformer-based NLP Models","date":"2023-05-23","arxiv_id":"2305.14453","n_code_links":1,"syntology":null},{"paper":"/paper/towards-massively-multi-domain-multilingual","slug":"towards-massively-multi-domain-multilingual","title":"ReadMe++: Benchmarking Multilingual Language Models for Multi-Domain Readability Assessment","date":"2023-05-23","arxiv_id":"2305.14463","n_code_links":1,"syntology":null},{"paper":"/paper/sparsefit-few-shot-prompting-with-sparse-fine","slug":"sparsefit-few-shot-prompting-with-sparse-fine","title":"SPARSEFIT: Few-shot Prompting with Sparse Fine-tuning for Jointly Generating Predictions and Natural Language Explanations","date":"2023-05-22","arxiv_id":"2305.13235","n_code_links":1,"syntology":null},{"paper":"/paper/model-generated-pretraining-signals-improves","slug":"model-generated-pretraining-signals-improves","title":"Model-Generated Pretraining Signals Improves Zero-Shot Generalization of Text-to-Text Transformers","date":"2023-05-21","arxiv_id":"2305.12567","n_code_links":1,"syntology":null},{"paper":null,"slug":"can-nlp-models-correctly-reason-over-contexts","title":"Can NLP Models Correctly Reason Over Contexts that Break the Common Assumptions?","date":"2023-05-20","arxiv_id":"2305.12096","n_code_links":0,"syntology":null},{"paper":null,"slug":"do-models-really-learn-to-follow-instructions","title":"Do Models Really Learn to Follow Instructions? An Empirical Study of Instruction Tuning","date":"2023-05-19","arxiv_id":"2305.11383","n_code_links":0,"syntology":null},{"paper":null,"slug":"generalized-multiple-intent-conditioned-slot","title":"Generalized Multiple Intent Conditioned Slot Filling","date":"2023-05-18","arxiv_id":"2305.11023","n_code_links":0,"syntology":null},{"paper":"/paper/mlongt5-a-multilingual-and-efficient-text-to","slug":"mlongt5-a-multilingual-and-efficient-text-to","title":"mLongT5: A Multilingual and Efficient Text-To-Text Transformer for Longer Sequences","date":"2023-05-18","arxiv_id":"2305.11129","n_code_links":1,"syntology":null},{"paper":"/paper/instruction-tuned-models-are-quick-learners","slug":"instruction-tuned-models-are-quick-learners","title":"Instruction Tuned Models are Quick Learners","date":"2023-05-17","arxiv_id":"2306.05539","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["srsawant34/efficient_instruction_learning"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/document-understanding-dataset-and-evaluation","slug":"document-understanding-dataset-and-evaluation","title":"Document Understanding Dataset and Evaluation (DUDE)","date":"2023-05-15","arxiv_id":"2305.08455","n_code_links":1,"syntology":{"ran":4,"of":5,"n_ran_checked":4,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["rubenpt91/MP-DocVQA-Framework"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"sensitivity-and-robustness-of-large-language","title":"Sensitivity and Robustness of Large Language Models to Prompt Template in Japanese Text Classification Tasks","date":"2023-05-15","arxiv_id":"2305.08714","n_code_links":0,"syntology":null},{"paper":"/paper/nl2tl-transforming-natural-languages-to","slug":"nl2tl-transforming-natural-languages-to","title":"NL2TL: Transforming Natural Languages to Temporal Logics using Large Language Models","date":"2023-05-12","arxiv_id":"2305.07766","n_code_links":3,"syntology":{"ran":5,"of":9,"n_ran_checked":2,"n_instrument":3,"unverified":4,"pointer_only":8,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified","official":{"repos":["yongchao98/nl2tl"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official","unlocated"]}}},{"paper":null,"slug":"rnns-representation-nearest-neighbor-search","title":"A Black-Box Attack on Code Models via Representation Nearest Neighbor Search","date":"2023-05-10","arxiv_id":"2305.05896","n_code_links":0,"syntology":null},{"paper":"/paper/an-exploration-of-encoder-decoder-approaches","slug":"an-exploration-of-encoder-decoder-approaches","title":"An Exploration of Encoder-Decoder Approaches to Multi-Label Classification for Legal and Biomedical Text","date":"2023-05-09","arxiv_id":"2305.05627","n_code_links":1,"syntology":null},{"paper":null,"slug":"multi-task-end-to-end-training-improves-1","title":"Multi-Task End-to-End Training Improves Conversational Recommendation","date":"2023-05-08","arxiv_id":"2305.06218","n_code_links":0,"syntology":null},{"paper":"/paper/distilling-step-by-step-outperforming-larger","slug":"distilling-step-by-step-outperforming-larger","title":"Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes","date":"2023-05-03","arxiv_id":"2305.02301","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":4,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["google-research/distilling-step-by-step"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/entity-tracking-in-language-models","slug":"entity-tracking-in-language-models","title":"Entity Tracking in Language Models","date":"2023-05-03","arxiv_id":"2305.02363","n_code_links":1,"syntology":null},{"paper":null,"slug":"training-and-evaluation-of-a-multilingual","title":"Training and Evaluation of a Multilingual Tokenizer for GPT-SW3","date":"2023-04-28","arxiv_id":"2304.14780","n_code_links":0,"syntology":null},{"paper":null,"slug":"neural-keyphrase-generation-analysis-and-1","title":"Neural Keyphrase Generation: Analysis and Evaluation","date":"2023-04-27","arxiv_id":"2304.13883","n_code_links":0,"syntology":null},{"paper":"/paper/introducing-mbib-the-first-media-bias","slug":"introducing-mbib-the-first-media-bias","title":"Introducing MBIB -- the first Media Bias Identification Benchmark Task and Dataset Collection","date":"2023-04-25","arxiv_id":"2304.13148","n_code_links":1,"syntology":null},{"paper":null,"slug":"semantic-tokenizer-for-enhanced-natural-1","title":"Semantic Tokenizer for Enhanced Natural Language Processing","date":"2023-04-24","arxiv_id":"2304.12404","n_code_links":0,"syntology":null},{"paper":"/paper/text-to-audio-generation-using-instruction","slug":"text-to-audio-generation-using-instruction","title":"Text-to-Audio Generation using Instruction-Tuned LLM and Latent Diffusion Model","date":"2023-04-24","arxiv_id":"2304.13731","n_code_links":1,"syntology":null},{"paper":null,"slug":"domain-specific-continued-pretraining-of","title":"Domain-specific Continued Pretraining of Language Models for Capturing Long Context in Mental Health","date":"2023-04-20","arxiv_id":"2304.10447","n_code_links":0,"syntology":null},{"paper":"/paper/longform-optimizing-instruction-tuning-for","slug":"longform-optimizing-instruction-tuning-for","title":"LongForm: Effective Instruction Tuning with Reverse Instructions","date":"2023-04-17","arxiv_id":"2304.08460","n_code_links":2,"syntology":null},{"paper":"/paper/the-minipile-challenge-for-data-efficient","slug":"the-minipile-challenge-for-data-efficient","title":"The MiniPile Challenge for Data-Efficient Language Models","date":"2023-04-17","arxiv_id":"2304.08442","n_code_links":1,"syntology":null},{"paper":null,"slug":"automated-program-repair-based-on-code-review","title":"Enhancing Automated Program Repair through Fine-tuning and Prompt Engineering","date":"2023-04-16","arxiv_id":"2304.07840","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-the-use-of-foundation-models-for","title":"Exploring the Use of Foundation Models for Named Entity Recognition and Lemmatization Tasks in Slavic Languages","date":"2023-04-11","arxiv_id":"2304.05336","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-learning-for-opinion-mining-and-topic","title":"Deep Learning for Opinion Mining and Topic Classification of Course Reviews","date":"2023-04-06","arxiv_id":"2304.03394","n_code_links":0,"syntology":null},{"paper":"/paper/chartreader-a-unified-framework-for-chart","slug":"chartreader-a-unified-framework-for-chart","title":"ChartReader: A Unified Framework for Chart Derendering and Comprehension without Heuristic Rules","date":"2023-04-05","arxiv_id":"2304.02173","n_code_links":1,"syntology":{"ran":16,"of":19,"n_ran_checked":6,"n_instrument":10,"unverified":3,"pointer_only":19,"phrase":"16 ran (of which 3 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 10 where Syntology's instrument failed) · 3 unverified","official":{"repos":["zhiqic/chartreader"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":3,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/generating-natural-language-from-logic","slug":"generating-natural-language-from-logic","title":"Generating Natural Language from Logic Expressions with Structural Representation","date":"2023-04-04","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/peach-pre-training-sequence-to-sequence","slug":"peach-pre-training-sequence-to-sequence","title":"PEACH: Pre-Training Sequence-to-Sequence Multilingual Models for Translation with Semi-Supervised Pseudo-Parallel Document Generation","date":"2023-04-03","arxiv_id":"2304.01282","n_code_links":1,"syntology":null},{"paper":"/paper/the-statcan-dialogue-dataset-retrieving-data","slug":"the-statcan-dialogue-dataset-retrieving-data","title":"The StatCan Dialogue Dataset: Retrieving Data Tables through Conversations with Genuine Intents","date":"2023-04-03","arxiv_id":"2304.01412","n_code_links":1,"syntology":null},{"paper":"/paper/understanding-individual-and-team-based-human","slug":"understanding-individual-and-team-based-human","title":"Does Human Collaboration Enhance the Accuracy of Identifying LLM-Generated Deepfake Texts?","date":"2023-04-03","arxiv_id":"2304.01002","n_code_links":2,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["huashen218/llm-deepfake-human-study"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/better-language-models-of-code-through-self","slug":"better-language-models-of-code-through-self","title":"Better Language Models of Code through Self-Improvement","date":"2023-04-02","arxiv_id":"2304.01228","n_code_links":1,"syntology":null},{"paper":null,"slug":"synthesis-of-mathematical-programs-from","title":"Synthesis of Mathematical programs from Natural Language Specifications","date":"2023-03-30","arxiv_id":"2304.03287","n_code_links":0,"syntology":null},{"paper":null,"slug":"summarizing-indian-languages-using","title":"Summarizing Indian Languages using Multilingual Transformers based Models","date":"2023-03-29","arxiv_id":"2303.16657","n_code_links":0,"syntology":null},{"paper":"/paper/explicit-planning-helps-language-models-in","slug":"explicit-planning-helps-language-models-in","title":"Explicit Planning Helps Language Models in Logical Reasoning","date":"2023-03-28","arxiv_id":"2303.15714","n_code_links":2,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","official":{"repos":["cindermond/explicit-planning-for-reasoning","cindermond/leap"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}}],"record_sha256":"f8fc2f816512a80a73679fa50cd6a60f55a7b6fc7f696f56dc85932978eb13ef","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}