{"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/adafactor/papers/2","list_of":"/method/adafactor","method":"Adafactor","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":2,"pages_in_order":8,"rows_per_page":100,"rows":[101,200],"of":733,"counts":{"archive_papers_tagged":733,"with_a_code_link":363,"where_syntology_ran_a_sample":103,"not_listed_spam_title":0,"listed":733,"listed_where_code_ran":103,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":89,"every_run_a_failure_of_syntologys_instrument":14,"listed_with_a_run_with_no_instrument_failure":89,"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/adafactor","prev":"/method/adafactor","next":"/method/adafactor/papers/3","papers":[{"paper":null,"slug":"small-language-models-are-equation-reasoners","title":"Small Language Models are Equation Reasoners","date":"2024-09-19","arxiv_id":"2409.12393","n_code_links":0,"syntology":null},{"paper":null,"slug":"chain-of-thought-prompting-for-speech","title":"Chain-of-Thought Prompting for Speech Translation","date":"2024-09-17","arxiv_id":"2409.11538","n_code_links":0,"syntology":null},{"paper":"/paper/soap-improving-and-stabilizing-shampoo-using","slug":"soap-improving-and-stabilizing-shampoo-using","title":"SOAP: Improving and Stabilizing Shampoo using Adam","date":"2024-09-17","arxiv_id":"2409.11321","n_code_links":1,"syntology":null},{"paper":null,"slug":"exploring-fine-tuned-generative-models-for","title":"Exploring Fine-tuned Generative Models for Keyphrase Selection: A Case Study for Russian","date":"2024-09-16","arxiv_id":"2409.10640","n_code_links":0,"syntology":null},{"paper":"/paper/playground-v3-improving-text-to-image","slug":"playground-v3-improving-text-to-image","title":"Playground v3: Improving Text-to-Image Alignment with Deep-Fusion Large Language Models","date":"2024-09-16","arxiv_id":"2409.10695","n_code_links":1,"syntology":{"ran":18,"of":21,"n_ran_checked":9,"n_instrument":9,"unverified":3,"pointer_only":21,"phrase":"18 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 4 honoured, 1 violated, 4 with no contract checked; 9 where Syntology's instrument failed) · 3 unverified","official":null}},{"paper":null,"slug":"detection-made-easy-potentials-of-large","title":"Detection Made Easy: Potentials of Large Language Models for Solidity Vulnerabilities","date":"2024-09-15","arxiv_id":"2409.10574","n_code_links":0,"syntology":null},{"paper":null,"slug":"robust-text-to-cypher-using-combination-of","title":"Robust Text-to-Cypher Using Combination of BERT, GraphSAGE, and Transformer (CoBGT) Model","date":"2024-09-04","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/masking-the-bias-from-echo-chambers-to-large","slug":"masking-the-bias-from-echo-chambers-to-large","title":"Masking The Bias : From Echo Chambers to Large Scale Aspect-Based Sentiment Analysis","date":"2024-09-02","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/maferw-query-rewriting-with-multi-aspect","slug":"maferw-query-rewriting-with-multi-aspect","title":"MaFeRw: Query Rewriting with Multi-Aspect Feedbacks for Retrieval-Augmented Large Language Models","date":"2024-08-30","arxiv_id":"2408.17072","n_code_links":1,"syntology":null},{"paper":null,"slug":"unintentional-security-flaws-in-code","title":"Unintentional Security Flaws in Code: Automated Defense via Root Cause Analysis","date":"2024-08-30","arxiv_id":"2409.00199","n_code_links":0,"syntology":null},{"paper":"/paper/mambaplace-text-to-point-cloud-cross-modal","slug":"mambaplace-text-to-point-cloud-cross-modal","title":"MambaPlace:Text-to-Point-Cloud Cross-Modal Place Recognition with Attention Mamba Mechanisms","date":"2024-08-28","arxiv_id":"2408.15740","n_code_links":1,"syntology":null},{"paper":null,"slug":"large-language-models-as-foundations-for-next","title":"Large Language Models as Foundations for Next-Gen Dense Retrieval: A Comprehensive Empirical Assessment","date":"2024-08-22","arxiv_id":"2408.12194","n_code_links":0,"syntology":null},{"paper":null,"slug":"factorized-dreamer-training-a-high-quality","title":"Factorized-Dreamer: Training A High-Quality Video Generator with Limited and Low-Quality Data","date":"2024-08-19","arxiv_id":"2408.10119","n_code_links":0,"syntology":null},{"paper":null,"slug":"tba-faster-large-language-model-training","title":"SSDTrain: An Activation Offloading Framework to SSDs for Faster Large Language Model Training","date":"2024-08-19","arxiv_id":"2408.10013","n_code_links":0,"syntology":null},{"paper":"/paper/datavist5-a-pre-trained-language-model-for","slug":"datavist5-a-pre-trained-language-model-for","title":"DataVisT5: A Pre-trained Language Model for Jointly Understanding Text and Data Visualization","date":"2024-08-14","arxiv_id":"2408.07401","n_code_links":1,"syntology":null},{"paper":null,"slug":"vulcatch-enhancing-binary-vulnerability","title":"VulCatch: Enhancing Binary Vulnerability Detection through CodeT5 Decompilation and KAN Advanced Feature Extraction","date":"2024-08-13","arxiv_id":"2408.07181","n_code_links":0,"syntology":null},{"paper":"/paper/2408-02976","slug":"2408-02976","title":"Empathy Level Alignment via Reinforcement Learning for Empathetic Response Generation","date":"2024-08-06","arxiv_id":"2408.02976","n_code_links":1,"syntology":null},{"paper":null,"slug":"2408-00921","title":"Automatic Pull Request Description Generation Using LLMs: A T5 Model Approach","date":"2024-08-01","arxiv_id":"2408.00921","n_code_links":0,"syntology":null},{"paper":"/paper/comparison-of-large-language-models-for","slug":"comparison-of-large-language-models-for","title":"Comparison of Large Language Models for Generating Contextually Relevant Questions","date":"2024-07-30","arxiv_id":"2407.20578","n_code_links":1,"syntology":null},{"paper":null,"slug":"sentiment-analysis-of-lithuanian-online","title":"Sentiment Analysis of Lithuanian Online Reviews Using Large Language Models","date":"2024-07-29","arxiv_id":"2407.19914","n_code_links":0,"syntology":null},{"paper":"/paper/positive-text-reframing-under-multi-strategy","slug":"positive-text-reframing-under-multi-strategy","title":"Positive Text Reframing under Multi-strategy Optimization","date":"2024-07-25","arxiv_id":"2407.17940","n_code_links":1,"syntology":null},{"paper":null,"slug":"reporting-and-analysing-the-environmental","title":"Reporting and Analysing the Environmental Impact of Language Models on the Example of Commonsense Question Answering with External Knowledge","date":"2024-07-24","arxiv_id":"2408.01453","n_code_links":0,"syntology":null},{"paper":"/paper/promises-and-pitfalls-of-generative-masked","slug":"promises-and-pitfalls-of-generative-masked","title":"Promises and Pitfalls of Generative Masked Language Modeling: Theoretical Framework and Practical Guidelines","date":"2024-07-22","arxiv_id":"2407.21046","n_code_links":1,"syntology":null},{"paper":"/paper/prior-knowledge-integration-via-llm-encoding","slug":"prior-knowledge-integration-via-llm-encoding","title":"Prior Knowledge Integration via LLM Encoding and Pseudo Event Regulation for Video Moment Retrieval","date":"2024-07-21","arxiv_id":"2407.15051","n_code_links":1,"syntology":{"ran":8,"of":11,"n_ran_checked":5,"n_instrument":3,"unverified":3,"pointer_only":9,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","official":{"repos":["fletcherjiang/llmepet"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"on-initializing-transformers-with-pre-trained","title":"On Initializing Transformers with Pre-trained Embeddings","date":"2024-07-17","arxiv_id":"2407.12514","n_code_links":0,"syntology":null},{"paper":"/paper/lami-detr-open-vocabulary-detection-with","slug":"lami-detr-open-vocabulary-detection-with","title":"LaMI-DETR: Open-Vocabulary Detection with Language Model Instruction","date":"2024-07-16","arxiv_id":"2407.11335","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":2,"n_instrument":1,"unverified":1,"pointer_only":0,"phrase":"3 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["eternaldolphin/lami-detr"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"weighted-grouped-query-attention-in","title":"Weighted Grouped Query Attention in Transformers","date":"2024-07-15","arxiv_id":"2407.10855","n_code_links":0,"syntology":null},{"paper":"/paper/youtube-sl-25-a-large-scale-open-domain","slug":"youtube-sl-25-a-large-scale-open-domain","title":"YouTube-SL-25: A Large-Scale, Open-Domain Multilingual Sign Language Parallel Corpus","date":"2024-07-15","arxiv_id":"2407.11144","n_code_links":1,"syntology":null},{"paper":null,"slug":"enhancing-emotion-prediction-in-news","title":"Enhancing Emotion Prediction in News Headlines: Insights from ChatGPT and Seq2Seq Models for Free-Text Generation","date":"2024-07-14","arxiv_id":"2407.10091","n_code_links":0,"syntology":null},{"paper":null,"slug":"surgical-text-to-image-generation","title":"Surgical Text-to-Image Generation","date":"2024-07-12","arxiv_id":"2407.09230","n_code_links":0,"syntology":null},{"paper":null,"slug":"deconstructing-what-makes-a-good-optimizer","title":"Deconstructing What Makes a Good Optimizer for Language Models","date":"2024-07-10","arxiv_id":"2407.07972","n_code_links":0,"syntology":null},{"paper":null,"slug":"segment-based-interactive-machine-translation","title":"Segment-Based Interactive Machine Translation for Pre-trained Models","date":"2024-07-09","arxiv_id":"2407.06990","n_code_links":0,"syntology":null},{"paper":null,"slug":"vision-braille-an-end-to-end-tool-for-chinese","title":"Vision-Braille: An End-to-End Tool for Chinese Braille Image-to-Text Translation","date":"2024-07-08","arxiv_id":"2407.06048","n_code_links":0,"syntology":null},{"paper":null,"slug":"rdbe-reasoning-distillation-based-evaluation","title":"RDBE: Reasoning Distillation-Based Evaluation Enhances Automatic Essay Scoring","date":"2024-07-03","arxiv_id":"2407.13781","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-model-arena-for-cross-lingual-sentiment","title":"The Model Arena for Cross-lingual Sentiment Analysis: A Comparative Study in the Era of Large Language Models","date":"2024-06-27","arxiv_id":"2406.19358","n_code_links":0,"syntology":null},{"paper":null,"slug":"relation-extraction-with-fine-tuned-large","title":"Relation Extraction with Fine-Tuned Large Language Models in Retrieval Augmented Generation Frameworks","date":"2024-06-20","arxiv_id":"2406.14745","n_code_links":0,"syntology":null},{"paper":null,"slug":"ptt5-v2-a-closer-look-at-continued","title":"ptt5-v2: A Closer Look at Continued Pretraining of T5 Models for the Portuguese Language","date":"2024-06-16","arxiv_id":"2406.10806","n_code_links":0,"syntology":null},{"paper":"/paper/re-rag-improving-open-domain-qa-performance","slug":"re-rag-improving-open-domain-qa-performance","title":"RE-RAG: Improving Open-Domain QA Performance and Interpretability with Relevance Estimator in Retrieval-Augmented Generation","date":"2024-06-09","arxiv_id":"2406.05794","n_code_links":1,"syntology":null},{"paper":null,"slug":"concept-formation-and-alignment-in-language","title":"Concept Formation and Alignment in Language Models: Bridging Statistical Patterns in Latent Space to Concept Taxonomy","date":"2024-06-08","arxiv_id":"2406.05315","n_code_links":0,"syntology":null},{"paper":"/paper/diner-a-large-realistic-dataset-for","slug":"diner-a-large-realistic-dataset-for","title":"DiNeR: a Large Realistic Dataset for Evaluating Compositional Generalization","date":"2024-06-07","arxiv_id":"2406.04669","n_code_links":1,"syntology":null},{"paper":"/paper/heidelberg-boston-sigtyp-2024-shared-task","slug":"heidelberg-boston-sigtyp-2024-shared-task","title":"Heidelberg-Boston @ SIGTYP 2024 Shared Task: Enhancing Low-Resource Language Analysis With Character-Aware Hierarchical Transformers","date":"2024-05-30","arxiv_id":"2405.20145","n_code_links":1,"syntology":null},{"paper":null,"slug":"kerascv-and-kerasnlp-vision-and-language","title":"KerasCV and KerasNLP: Vision and Language Power-Ups","date":"2024-05-30","arxiv_id":"2405.20247","n_code_links":0,"syntology":null},{"paper":null,"slug":"faster-cascades-via-speculative-decoding","title":"Faster Cascades via Speculative Decoding","date":"2024-05-29","arxiv_id":"2405.19261","n_code_links":0,"syntology":null},{"paper":null,"slug":"offline-regularised-reinforcement-learning","title":"Offline Regularised Reinforcement Learning for Large Language Models Alignment","date":"2024-05-29","arxiv_id":"2405.19107","n_code_links":0,"syntology":null},{"paper":"/paper/deeperimpact-optimizing-sparse-learned-index","slug":"deeperimpact-optimizing-sparse-learned-index","title":"DeeperImpact: Optimizing Sparse Learned Index Structures","date":"2024-05-27","arxiv_id":"2405.17093","n_code_links":1,"syntology":null},{"paper":null,"slug":"masked-face-recognition-with-generative-to","title":"Masked Face Recognition with Generative-to-Discriminative Representations","date":"2024-05-27","arxiv_id":"2405.16761","n_code_links":0,"syntology":null},{"paper":null,"slug":"polyak-meets-parameter-free-clipped-gradient","title":"Parameter-free Clipped Gradient Descent Meets Polyak","date":"2024-05-23","arxiv_id":"2405.15010","n_code_links":0,"syntology":null},{"paper":null,"slug":"surge-phenomenon-in-optimal-learning-rate-and","title":"Surge Phenomenon in Optimal Learning Rate and Batch Size Scaling","date":"2024-05-23","arxiv_id":"2405.14578","n_code_links":0,"syntology":null},{"paper":null,"slug":"igot-information-gain-optimized-tokenizer-on","title":"IGOT: Information Gain Optimized Tokenizer on Domain Adaptive Pretraining","date":"2024-05-16","arxiv_id":"2405.09857","n_code_links":0,"syntology":null},{"paper":"/paper/depth-discourse-education-through-pre","slug":"depth-discourse-education-through-pre","title":"DEPTH: Discourse Education through Pre-Training Hierarchically","date":"2024-05-13","arxiv_id":"2405.07788","n_code_links":1,"syntology":null},{"paper":null,"slug":"evaluating-text-summaries-generated-by-large","title":"Evaluating Text Summaries Generated by Large Language Models Using OpenAI's GPT","date":"2024-05-07","arxiv_id":"2405.04053","n_code_links":0,"syntology":null},{"paper":null,"slug":"utilizing-gpt-to-enhance-text-summarization-a","title":"Utilizing GPT to Enhance Text Summarization: A Strategy to Minimize Hallucinations","date":"2024-05-07","arxiv_id":"2405.04039","n_code_links":0,"syntology":null},{"paper":null,"slug":"assessing-adversarial-robustness-of-large","title":"Assessing Adversarial Robustness of Large Language Models: An Empirical Study","date":"2024-05-04","arxiv_id":"2405.02764","n_code_links":0,"syntology":null},{"paper":"/paper/uqa-corpus-for-urdu-question-answering","slug":"uqa-corpus-for-urdu-question-answering","title":"UQA: Corpus for Urdu Question Answering","date":"2024-05-02","arxiv_id":"2405.01458","n_code_links":3,"syntology":null},{"paper":"/paper/opinion-mining-using-pre-trained-large","slug":"opinion-mining-using-pre-trained-large","title":"Opinion Mining Using Pre-Trained Large Language Models: Identifying the Type, Polarity, Intensity, Expression, and Source of Private States","date":"2024-05-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"transferring-troubles-cross-lingual","title":"TuBA: Cross-Lingual Transferability of Backdoor Attacks in LLMs with Instruction Tuning","date":"2024-04-30","arxiv_id":"2404.19597","n_code_links":0,"syntology":null},{"paper":"/paper/indicgenbench-a-multilingual-benchmark-to","slug":"indicgenbench-a-multilingual-benchmark-to","title":"IndicGenBench: A Multilingual Benchmark to Evaluate Generation Capabilities of LLMs on Indic Languages","date":"2024-04-25","arxiv_id":"2404.16816","n_code_links":1,"syntology":null},{"paper":null,"slug":"augmenting-emotion-features-in-irony","title":"Augmenting emotion features in irony detection with Large language modeling","date":"2024-04-18","arxiv_id":"2404.12291","n_code_links":0,"syntology":null},{"paper":"/paper/comparative-analysis-of-deep-natural-networks","slug":"comparative-analysis-of-deep-natural-networks","title":"Comparative Analysis of Deep Natural Networks and Large Language Models for Aspect-Based Sentiment Analysis","date":"2024-04-17","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"hltcoe-at-trec-2023-neuclir-track","title":"HLTCOE at TREC 2023 NeuCLIR Track","date":"2024-04-11","arxiv_id":"2404.08118","n_code_links":0,"syntology":null},{"paper":null,"slug":"medical-mt5-an-open-source-multilingual-text","title":"Medical mT5: An Open-Source Multilingual Text-to-Text LLM for The Medical Domain","date":"2024-04-11","arxiv_id":"2404.07613","n_code_links":0,"syntology":null},{"paper":"/paper/control-dag-constrained-decoding-for-non","slug":"control-dag-constrained-decoding-for-non","title":"Control-DAG: Constrained Decoding for Non-Autoregressive Directed Acyclic T5 using Weighted Finite State Automata","date":"2024-04-10","arxiv_id":"2404.06854","n_code_links":1,"syntology":null},{"paper":"/paper/data-bias-according-to-bipol-men-are","slug":"data-bias-according-to-bipol-men-are","title":"Data Bias According to Bipol: Men are Naturally Right and It is the Role of Women to Follow Their Lead","date":"2024-04-07","arxiv_id":"2404.04838","n_code_links":1,"syntology":null},{"paper":"/paper/adaptive-cross-lingual-text-classification","slug":"adaptive-cross-lingual-text-classification","title":"Adaptive Cross-lingual Text Classification through In-Context One-Shot Demonstrations","date":"2024-04-03","arxiv_id":"2404.02452","n_code_links":1,"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":["villacu/ic_xlt"],"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":null,"slug":"on-linearizing-structured-data-in-encoder","title":"On Linearizing Structured Data in Encoder-Decoder Language Models: Insights from Text-to-SQL","date":"2024-04-03","arxiv_id":"2404.02389","n_code_links":0,"syntology":null},{"paper":"/paper/mitigating-misleading-chain-of-thought","slug":"mitigating-misleading-chain-of-thought","title":"Mitigating Misleading Chain-of-Thought Reasoning with Selective Filtering","date":"2024-03-28","arxiv_id":"2403.19167","n_code_links":1,"syntology":null},{"paper":"/paper/reshaping-free-text-radiology-notes-into","slug":"reshaping-free-text-radiology-notes-into","title":"Reshaping Free-Text Radiology Notes Into Structured Reports With Generative Transformers","date":"2024-03-27","arxiv_id":"2403.18938","n_code_links":1,"syntology":null},{"paper":null,"slug":"multilingual-sentence-t5-scalable-sentence","title":"Multilingual Sentence-T5: Scalable Sentence Encoders for Multilingual Applications","date":"2024-03-26","arxiv_id":"2403.17528","n_code_links":0,"syntology":null},{"paper":null,"slug":"transcribing-bengali-text-with-regional","title":"Transcribing Bengali Text with Regional Dialects to IPA using District Guided Tokens","date":"2024-03-26","arxiv_id":"2403.17407","n_code_links":0,"syntology":null},{"paper":null,"slug":"concurrent-linguistic-error-detection-cled","title":"Concurrent Linguistic Error Detection (CLED) for Large Language Models","date":"2024-03-25","arxiv_id":"2403.16393","n_code_links":0,"syntology":null},{"paper":null,"slug":"r3cd-scene-graph-to-image-generation-with","title":"R3CD: Scene Graph to Image Generation with Relation-aware Compositional Contrastive Control Diffusion","date":"2024-03-24","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"adapprox-adaptive-approximation-in-adam","title":"Adapprox: Adaptive Approximation in Adam Optimization via Randomized Low-Rank Matrices","date":"2024-03-22","arxiv_id":"2403.14958","n_code_links":0,"syntology":null},{"paper":null,"slug":"sensoryt5-infusing-sensorimotor-norms-into-t5","title":"SensoryT5: Infusing Sensorimotor Norms into T5 for Enhanced Fine-grained Emotion Classification","date":"2024-03-22","arxiv_id":"2403.15574","n_code_links":0,"syntology":null},{"paper":null,"slug":"automatic-summarization-of-doctor-patient","title":"Automatic Summarization of Doctor-Patient Encounter Dialogues Using Large Language Model through Prompt Tuning","date":"2024-03-19","arxiv_id":"2403.13089","n_code_links":0,"syntology":null},{"paper":"/paper/evaluating-named-entity-recognition","slug":"evaluating-named-entity-recognition","title":"Evaluating Named Entity Recognition: A comparative analysis of mono- and multilingual transformer models on a novel Brazilian corporate earnings call transcripts dataset","date":"2024-03-18","arxiv_id":"2403.12212","n_code_links":2,"syntology":null},{"paper":"/paper/empirical-studies-of-parameter-efficient","slug":"empirical-studies-of-parameter-efficient","title":"Empirical Studies of Parameter Efficient Methods for Large Language Models of Code and Knowledge Transfer to R","date":"2024-03-16","arxiv_id":"2405.01553","n_code_links":1,"syntology":null},{"paper":null,"slug":"exegpt-constraint-aware-resource-scheduling","title":"ExeGPT: Constraint-Aware Resource Scheduling for LLM Inference","date":"2024-03-15","arxiv_id":"2404.07947","n_code_links":0,"syntology":null},{"paper":null,"slug":"basque-and-spanish-counter-narrative","title":"Basque and Spanish Counter Narrative Generation: Data Creation and Evaluation","date":"2024-03-14","arxiv_id":"2403.09159","n_code_links":0,"syntology":null},{"paper":null,"slug":"information-extraction-an-application-to-the","title":"Information Extraction: An application to the domain of hyper-local financial data on developing countries","date":"2024-03-14","arxiv_id":"2403.09077","n_code_links":0,"syntology":null},{"paper":"/paper/autoregressive-score-generation-for-multi","slug":"autoregressive-score-generation-for-multi","title":"Autoregressive Score Generation for Multi-trait Essay Scoring","date":"2024-03-13","arxiv_id":"2403.08332","n_code_links":1,"syntology":null},{"paper":null,"slug":"embedded-translations-for-low-resource","title":"Embedded Translations for Low-resource Automated Glossing","date":"2024-03-13","arxiv_id":"2403.08189","n_code_links":0,"syntology":null},{"paper":"/paper/chronos-learning-the-language-of-time-series","slug":"chronos-learning-the-language-of-time-series","title":"Chronos: Learning the Language of Time Series","date":"2024-03-12","arxiv_id":"2403.07815","n_code_links":6,"syntology":{"ran":23,"of":28,"n_ran_checked":22,"n_instrument":1,"unverified":5,"pointer_only":5,"phrase":"23 ran (of which 0 constructed an object rather than computing a result; 22 with no instrument failure: 3 honoured, 1 violated, 18 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","official":{"repos":["SalesforceAIResearch/uni2ts","amazon-science/chronos-forecasting"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/contextual-clarity-generating-sentences-with","slug":"contextual-clarity-generating-sentences-with","title":"Contextual Clarity: Generating Sentences with Transformer Models using Context-Reverso Data","date":"2024-03-12","arxiv_id":"2403.08103","n_code_links":1,"syntology":null},{"paper":"/paper/linguistic-knowledge-can-enhance-encoder","slug":"linguistic-knowledge-can-enhance-encoder","title":"Linguistic Knowledge Can Enhance Encoder-Decoder Models (If You Let It)","date":"2024-02-27","arxiv_id":"2402.17608","n_code_links":1,"syntology":null},{"paper":null,"slug":"skt5scisumm-a-hybrid-generative-approach-for","title":"SKT5SciSumm -- Revisiting Extractive-Generative Approach for Multi-Document Scientific Summarization","date":"2024-02-27","arxiv_id":"2402.17311","n_code_links":0,"syntology":null},{"paper":null,"slug":"esg-sentiment-analysis-comparing-human-and","title":"ESG Sentiment Analysis: comparing human and language model performance including GPT","date":"2024-02-26","arxiv_id":"2402.16650","n_code_links":0,"syntology":null},{"paper":"/paper/advancing-parameter-efficiency-in-fine-tuning","slug":"advancing-parameter-efficiency-in-fine-tuning","title":"Advancing Parameter Efficiency in Fine-tuning via Representation Editing","date":"2024-02-23","arxiv_id":"2402.15179","n_code_links":2,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","official":{"repos":["mlwu22/red"],"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":["listed","official"]}}},{"paper":"/paper/annotation-and-classification-of-relevant","slug":"annotation-and-classification-of-relevant","title":"Annotation and Classification of Relevant Clauses in Terms-and-Conditions Contracts","date":"2024-02-22","arxiv_id":"2402.14457","n_code_links":1,"syntology":null},{"paper":"/paper/umbclu-at-semeval-2024-task-1a-and-1c","slug":"umbclu-at-semeval-2024-task-1a-and-1c","title":"UMBCLU at SemEval-2024 Task 1A and 1C: Semantic Textual Relatedness with and without machine translation","date":"2024-02-20","arxiv_id":"2402.12730","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-synthetic-data-approach-for-domain","title":"A synthetic data approach for domain generalization of NLI models","date":"2024-02-19","arxiv_id":"2402.12368","n_code_links":0,"syntology":null},{"paper":null,"slug":"key-ingredients-for-effective-zero-shot-cross","title":"Key ingredients for effective zero-shot cross-lingual knowledge transfer in generative tasks","date":"2024-02-19","arxiv_id":"2402.12279","n_code_links":0,"syntology":null},{"paper":null,"slug":"emerging-opportunities-of-using-large","title":"Emerging Opportunities of Using Large Language Models for Translation Between Drug Molecules and Indications","date":"2024-02-14","arxiv_id":"2402.09588","n_code_links":0,"syntology":null},{"paper":null,"slug":"fgeo-tp-a-language-model-enhanced-solver-for","title":"FGeo-TP: A Language Model-Enhanced Solver for Geometry Problems","date":"2024-02-14","arxiv_id":"2402.09047","n_code_links":0,"syntology":null},{"paper":"/paper/improving-black-box-robustness-with-in","slug":"improving-black-box-robustness-with-in","title":"Improving Black-box Robustness with In-Context Rewriting","date":"2024-02-13","arxiv_id":"2402.08225","n_code_links":1,"syntology":null},{"paper":"/paper/inksight-offline-to-online-handwriting","slug":"inksight-offline-to-online-handwriting","title":"InkSight: Offline-to-Online Handwriting Conversion by Learning to Read and Write","date":"2024-02-08","arxiv_id":"2402.05804","n_code_links":1,"syntology":null},{"paper":null,"slug":"lens-a-foundation-model-for-network-traffic","title":"Lens: A Foundation Model for Network Traffic","date":"2024-02-06","arxiv_id":"2402.03646","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-a-unified-language-model-for","title":"CorpusLM: Towards a Unified Language Model on Corpus for Knowledge-Intensive Tasks","date":"2024-02-02","arxiv_id":"2402.01176","n_code_links":0,"syntology":null},{"paper":null,"slug":"what-will-my-model-forget-forecasting","title":"What Will My Model Forget? Forecasting Forgotten Examples in Language Model Refinement","date":"2024-02-02","arxiv_id":"2402.01865","n_code_links":0,"syntology":null},{"paper":"/paper/improving-semantic-control-in-discrete-latent","slug":"improving-semantic-control-in-discrete-latent","title":"Improving Semantic Control in Discrete Latent Spaces with Transformer Quantized Variational Autoencoders","date":"2024-02-01","arxiv_id":"2402.00723","n_code_links":1,"syntology":null},{"paper":"/paper/topro-token-level-prompt-decomposition-for","slug":"topro-token-level-prompt-decomposition-for","title":"ToPro: Token-Level Prompt Decomposition for Cross-Lingual Sequence Labeling Tasks","date":"2024-01-29","arxiv_id":"2401.16589","n_code_links":1,"syntology":null}],"record_sha256":"d87891bd10e9630931dc4064f5190d6bbf067f00f79e7fcc2957c3aa7e1de11b","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}