{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/language-modeling/papers/96","list_of":"/task/language-modeling","task":"Language Modeling","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":96,"pages_in_order":142,"rows_per_page":100,"rows":[9501,9600],"of":14182,"counts":{"archive_papers_tagged":14182,"with_a_code_link":5620,"where_syntology_ran_a_sample":1894,"not_listed_spam_title":0,"listed":14182,"listed_where_code_ran":1894,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1580,"every_run_a_failure_of_syntologys_instrument":314,"listed_with_a_run_with_no_instrument_failure":1580,"listed_every_run_a_failure_of_syntologys_instrument":314,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/language-modeling","prev":"/task/language-modeling/papers/95","next":"/task/language-modeling/papers/97","papers":[{"url":null,"slug":"rephrasing-the-web-a-recipe-for-compute-and","title":"Rephrasing the Web: A Recipe for Compute and Data-Efficient Language Modeling","date":"2024-01-29","arxiv_id":"2401.16380","repositories_listed":0,"syntology":null},{"url":null,"slug":"routers-in-vision-mixture-of-experts-an","title":"Routers in Vision Mixture of Experts: An Empirical Study","date":"2024-01-29","arxiv_id":"2401.15969","repositories_listed":0,"syntology":null},{"url":null,"slug":"x-peft-extremely-parameter-efficient-fine","title":"X-PEFT: eXtremely Parameter-Efficient Fine-Tuning for Extreme Multi-Profile Scenarios","date":"2024-01-29","arxiv_id":"2401.16137","repositories_listed":0,"syntology":null},{"url":null,"slug":"you-tell-me-a-dataset-of-gpt-4-based","title":"\"You tell me\": A Dataset of GPT-4-Based Behaviour Change Support Conversations","date":"2024-01-29","arxiv_id":"2401.16167","repositories_listed":0,"syntology":null},{"url":null,"slug":"llm4sechw-leveraging-domain-specific-large","title":"LLM4SecHW: Leveraging Domain Specific Large Language Model for Hardware Debugging","date":"2024-01-28","arxiv_id":"2401.16448","repositories_listed":0,"syntology":null},{"url":null,"slug":"pre-a-peer-review-based-large-language-model","title":"PRE: A Peer Review Based Large Language Model Evaluator","date":"2024-01-28","arxiv_id":"2401.15641","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-large-language-model-performance-to","title":"Enhancing Large Language Model Performance To Answer Questions and Extract Information More Accurately","date":"2024-01-27","arxiv_id":"2402.01722","repositories_listed":0,"syntology":null},{"url":null,"slug":"equipping-language-models-with-tool-use","title":"Equipping Language Models with Tool Use Capability for Tabular Data Analysis in Finance","date":"2024-01-27","arxiv_id":"2401.15328","repositories_listed":0,"syntology":null},{"url":null,"slug":"hardware-phi-1-5b-a-large-language-model","title":"Hardware Phi-1.5B: A Large Language Model Encodes Hardware Domain Specific Knowledge","date":"2024-01-27","arxiv_id":"2402.01728","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-empirical-investigation-of-domain-1","title":"An Empirical Investigation of Domain Adaptation Ability for Chinese Spelling Check Models","date":"2024-01-26","arxiv_id":"2401.14630","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-model-adaptation-for-financial","title":"Large Language Model Adaptation for Financial Sentiment Analysis","date":"2024-01-26","arxiv_id":"2401.14777","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-model-guided-knowledge","title":"Large Language Model Guided Knowledge Distillation for Time Series Anomaly Detection","date":"2024-01-26","arxiv_id":"2401.15123","repositories_listed":0,"syntology":null},{"url":null,"slug":"mallam-malaysia-large-language-model","title":"MaLLaM -- Malaysia Large Language Model","date":"2024-01-26","arxiv_id":"2401.14680","repositories_listed":0,"syntology":null},{"url":null,"slug":"measuring-moral-inconsistencies-in-large","title":"Measuring Moral Inconsistencies in Large Language Models","date":"2024-01-26","arxiv_id":"2402.01719","repositories_listed":0,"syntology":null},{"url":null,"slug":"query-of-cc-unearthing-large-scale-domain","title":"Query of CC: Unearthing Large Scale Domain-Specific Knowledge from Public Corpora","date":"2024-01-26","arxiv_id":"2401.14624","repositories_listed":0,"syntology":null},{"url":null,"slug":"spatial-transcriptomics-analysis-of-zero-shot","title":"Spatial Transcriptomics Analysis of Zero-shot Gene Expression Prediction","date":"2024-01-26","arxiv_id":"2401.14772","repositories_listed":0,"syntology":null},{"url":null,"slug":"turn-taking-and-backchannel-prediction-with","title":"Turn-taking and Backchannel Prediction with Acoustic and Large Language Model Fusion","date":"2024-01-26","arxiv_id":"2401.14717","repositories_listed":0,"syntology":null},{"url":null,"slug":"accelerating-retrieval-augmented-language","title":"Accelerating Retrieval-Augmented Language Model Serving with Speculation","date":"2024-01-25","arxiv_id":"2401.14021","repositories_listed":0,"syntology":null},{"url":null,"slug":"chatgpt-vs-gemini-vs-llama-on-multilingual","title":"ChatGPT vs Gemini vs LLaMA on Multilingual Sentiment Analysis","date":"2024-01-25","arxiv_id":"2402.01715","repositories_listed":0,"syntology":null},{"url":null,"slug":"do-not-always-look-right-investigating-the","title":"Looking Right is Sometimes Right: Investigating the Capabilities of Decoder-only LLMs for Sequence Labeling","date":"2024-01-25","arxiv_id":"2401.14556","repositories_listed":0,"syntology":null},{"url":null,"slug":"hi-core-hierarchical-knowledge-transfer-for","title":"Hierarchical Continual Reinforcement Learning via Large Language Model","date":"2024-01-25","arxiv_id":"2401.15098","repositories_listed":0,"syntology":null},{"url":null,"slug":"locmoe-a-low-overhead-moe-for-large-language","title":"LocMoE: A Low-Overhead MoE for Large Language Model Training","date":"2024-01-25","arxiv_id":"2401.13920","repositories_listed":0,"syntology":null},{"url":null,"slug":"multiverse-exposing-large-language-model","title":"MULTIVERSE: Exposing Large Language Model Alignment Problems in Diverse Worlds","date":"2024-01-25","arxiv_id":"2402.01706","repositories_listed":0,"syntology":null},{"url":null,"slug":"styleinject-parameter-efficient-tuning-of","title":"StyleInject: Parameter Efficient Tuning of Text-to-Image Diffusion Models","date":"2024-01-25","arxiv_id":"2401.13942","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-typing-cure-experiences-with-large","title":"The Typing Cure: Experiences with Large Language Model Chatbots for Mental Health Support","date":"2024-01-25","arxiv_id":"2401.14362","repositories_listed":0,"syntology":null},{"url":null,"slug":"higen-hierarchy-aware-sequence-generation-for","title":"HiGen: Hierarchy-Aware Sequence Generation for Hierarchical Text Classification","date":"2024-01-24","arxiv_id":"2402.01696","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-model-empowered-participatory","title":"Large language model empowered participatory urban planning","date":"2024-01-24","arxiv_id":"2402.01698","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-malaysian-language-model-based-on","title":"Large Malaysian Language Model Based on Mistral for Enhanced Local Language Understanding","date":"2024-01-24","arxiv_id":"2401.13565","repositories_listed":0,"syntology":null},{"url":null,"slug":"mala-500-massive-language-adaptation-of-large","title":"MaLA-500: Massive Language Adaptation of Large Language Models","date":"2024-01-24","arxiv_id":"2401.13303","repositories_listed":0,"syntology":null},{"url":null,"slug":"mambabyte-token-free-selective-state-space","title":"MambaByte: Token-free Selective State Space Model","date":"2024-01-24","arxiv_id":"2401.13660","repositories_listed":0,"syntology":null},{"url":null,"slug":"mllmreid-multimodal-large-language-model","title":"MLLMReID: Multimodal Large Language Model-based Person Re-identification","date":"2024-01-24","arxiv_id":"2401.13201","repositories_listed":0,"syntology":null},{"url":null,"slug":"supporting-sensemaking-of-large-language","title":"Supporting Sensemaking of Large Language Model Outputs at Scale","date":"2024-01-24","arxiv_id":"2401.13726","repositories_listed":0,"syntology":null},{"url":null,"slug":"tat-llm-a-specialized-language-model-for","title":"TAT-LLM: A Specialized Language Model for Discrete Reasoning over Tabular and Textual Data","date":"2024-01-24","arxiv_id":"2401.13223","repositories_listed":0,"syntology":null},{"url":null,"slug":"tpd-enhancing-student-language-model","title":"TPD: Enhancing Student Language Model Reasoning via Principle Discovery and Guidance","date":"2024-01-24","arxiv_id":"2401.13849","repositories_listed":0,"syntology":null},{"url":null,"slug":"chatgraph-chat-with-your-graphs","title":"ChatGraph: Chat with Your Graphs","date":"2024-01-23","arxiv_id":"2401.12672","repositories_listed":0,"syntology":null},{"url":null,"slug":"comparing-human-centered-language-modeling-is","title":"Comparing Pre-trained Human Language Models: Is it Better with Human Context as Groups, Individual Traits, or Both?","date":"2024-01-23","arxiv_id":"2401.12492","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-distillation-from-language-oriented","title":"Knowledge Distillation from Language-Oriented to Emergent Communication for Multi-Agent Remote Control","date":"2024-01-23","arxiv_id":"2401.12624","repositories_listed":0,"syntology":null},{"url":null,"slug":"multilingual-and-fully-non-autoregressive-asr","title":"Multilingual and Fully Non-Autoregressive ASR with Large Language Model Fusion: A Comprehensive Study","date":"2024-01-23","arxiv_id":"2401.12789","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-supervised-vision-transformers-are","title":"Self-Supervised Vision Transformers Are Efficient Segmentation Learners for Imperfect Labels","date":"2024-01-23","arxiv_id":"2401.12535","repositories_listed":0,"syntology":null},{"url":"/paper/small-language-model-meets-with-reinforced","slug":"small-language-model-meets-with-reinforced","title":"Small Language Model Meets with Reinforced Vision Vocabulary","date":"2024-01-23","arxiv_id":"2401.12503","repositories_listed":0,"syntology":null},{"url":null,"slug":"xai-for-all-can-large-language-models","title":"XAI for All: Can Large Language Models Simplify Explainable AI?","date":"2024-01-23","arxiv_id":"2401.13110","repositories_listed":0,"syntology":null},{"url":null,"slug":"zero-shot-open-ended-video-inference","title":"Training-Free Action Recognition and Goal Inference with Dynamic Frame Selection","date":"2024-01-23","arxiv_id":"2401.12471","repositories_listed":0,"syntology":null},{"url":null,"slug":"coavt-a-cognition-inspired-unified-audio","title":"CoAVT: A Cognition-Inspired Unified Audio-Visual-Text Pre-Training Model for Multimodal Processing","date":"2024-01-22","arxiv_id":"2401.12264","repositories_listed":0,"syntology":null},{"url":null,"slug":"keep-decoding-parallel-with-effective","title":"Keep Decoding Parallel with Effective Knowledge Distillation from Language Models to End-to-end Speech Recognisers","date":"2024-01-22","arxiv_id":"2401.11700","repositories_listed":0,"syntology":null},{"url":null,"slug":"signvtcl-multi-modal-continuous-sign-language","title":"SignVTCL: Multi-Modal Continuous Sign Language Recognition Enhanced by Visual-Textual Contrastive Learning","date":"2024-01-22","arxiv_id":"2401.11847","repositories_listed":0,"syntology":null},{"url":null,"slug":"west-of-n-synthetic-preference-generation-for","title":"West-of-N: Synthetic Preferences for Self-Improving Reward Models","date":"2024-01-22","arxiv_id":"2401.12086","repositories_listed":0,"syntology":null},{"url":null,"slug":"attentionlego-an-open-source-building-block","title":"AttentionLego: An Open-Source Building Block For Spatially-Scalable Large Language Model Accelerator With Processing-In-Memory Technology","date":"2024-01-21","arxiv_id":"2401.11459","repositories_listed":0,"syntology":null},{"url":null,"slug":"integration-of-large-language-models-in","title":"Integration of Large Language Models in Control of EHD Pumps for Precise Color Synthesis","date":"2024-01-21","arxiv_id":"2401.11500","repositories_listed":0,"syntology":null},{"url":null,"slug":"llmra-multi-modal-large-language-model-based","title":"LLMRA: Multi-modal Large Language Model based Restoration Assistant","date":"2024-01-21","arxiv_id":"2401.11401","repositories_listed":0,"syntology":null},{"url":null,"slug":"training-microrobots-to-swim-by-a-large","title":"Training microrobots to swim by a large language model","date":"2024-01-21","arxiv_id":"2402.00044","repositories_listed":0,"syntology":null},{"url":null,"slug":"using-large-language-model-for-end-to-end","title":"Using Large Language Model for End-to-End Chinese ASR and NER","date":"2024-01-21","arxiv_id":"2401.11382","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-simple-framework-to-accelerate-multilingual","title":"Accelerating Multilingual Language Model for Excessively Tokenized Languages","date":"2024-01-19","arxiv_id":"2401.10660","repositories_listed":0,"syntology":null},{"url":null,"slug":"critical-data-size-of-language-models-from-a","title":"Critical Data Size of Language Models from a Grokking Perspective","date":"2024-01-19","arxiv_id":"2401.10463","repositories_listed":0,"syntology":null},{"url":null,"slug":"investigating-training-strategies-and-model","title":"Investigating Training Strategies and Model Robustness of Low-Rank Adaptation for Language Modeling in Speech Recognition","date":"2024-01-19","arxiv_id":"2401.10447","repositories_listed":0,"syntology":null},{"url":null,"slug":"photobot-reference-guided-interactive","title":"PhotoBot: Reference-Guided Interactive Photography via Natural Language","date":"2024-01-19","arxiv_id":"2401.11061","repositories_listed":0,"syntology":null},{"url":null,"slug":"streamvoice-streamable-context-aware-language","title":"StreamVoice: Streamable Context-Aware Language Modeling for Real-time Zero-Shot Voice Conversion","date":"2024-01-19","arxiv_id":"2401.11053","repositories_listed":0,"syntology":null},{"url":null,"slug":"using-llms-to-discover-emerging-coded","title":"Using LLMs to discover emerging coded antisemitic hate-speech in extremist social media","date":"2024-01-19","arxiv_id":"2401.10841","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-fast-performant-secure-distributed-training","title":"A Fast, Performant, Secure Distributed Training Framework For Large Language Model","date":"2024-01-18","arxiv_id":"2401.09796","repositories_listed":0,"syntology":null},{"url":null,"slug":"advancing-large-multi-modal-models-with","title":"Advancing Large Multi-modal Models with Explicit Chain-of-Reasoning and Visual Question Generation","date":"2024-01-18","arxiv_id":"2401.10005","repositories_listed":0,"syntology":null},{"url":null,"slug":"automated-scoring-of-clinical-patient-notes","title":"Automated Scoring of Clinical Patient Notes using Advanced NLP and Pseudo Labeling","date":"2024-01-18","arxiv_id":"2401.12994","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-large-language-model-summarizers-adapt-to","title":"Can Large Language Model Summarizers Adapt to Diverse Scientific Communication Goals?","date":"2024-01-18","arxiv_id":"2401.10415","repositories_listed":0,"syntology":null},{"url":null,"slug":"evolutionary-multi-objective-optimization-of-1","title":"Evolutionary Multi-Objective Optimization of Large Language Model Prompts for Balancing Sentiments","date":"2024-01-18","arxiv_id":"2401.09862","repositories_listed":0,"syntology":null},{"url":null,"slug":"gradable-chatgpt-translation-evaluation","title":"Gradable ChatGPT Translation Evaluation","date":"2024-01-18","arxiv_id":"2401.09984","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-model-lateral-spear-phishing-a","title":"Lateral Phishing With Large Language Models: A Large Organization Comparative Study","date":"2024-01-18","arxiv_id":"2401.09727","repositories_listed":0,"syntology":null},{"url":null,"slug":"fine-tuning-strategies-for-domain-specific-1","title":"Fine-tuning Strategies for Domain Specific Question Answering under Low Annotation Budget Constraints","date":"2024-01-17","arxiv_id":"2401.09168","repositories_listed":0,"syntology":null},{"url":null,"slug":"impact-of-large-language-model-assistance-on","title":"Impact of Large Language Model Assistance on Patients Reading Clinical Notes: A Mixed-Methods Study","date":"2024-01-17","arxiv_id":"2401.09637","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-document-level-translation-of-large","title":"Enhancing Document-level Translation of Large Language Model via Translation Mixed-instructions","date":"2024-01-16","arxiv_id":"2401.08088","repositories_listed":0,"syntology":null},{"url":null,"slug":"multiply-a-multisensory-object-centric","title":"MultiPLY: A Multisensory Object-Centric Embodied Large Language Model in 3D World","date":"2024-01-16","arxiv_id":"2401.08577","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-imagine-effective-unimodal-reasoning","title":"Self-Imagine: Effective Unimodal Reasoning with Multimodal Models using Self-Imagination","date":"2024-01-16","arxiv_id":"2401.08025","repositories_listed":0,"syntology":null},{"url":null,"slug":"stability-analysis-of-chatgpt-based-sentiment","title":"Stability Analysis of ChatGPT-based Sentiment Analysis in AI Quality Assurance","date":"2024-01-15","arxiv_id":"2401.07441","repositories_listed":0,"syntology":null},{"url":null,"slug":"when-large-language-model-agents-meet-6g","title":"When Large Language Model Agents Meet 6G Networks: Perception, Grounding, and Alignment","date":"2024-01-15","arxiv_id":"2401.07764","repositories_listed":0,"syntology":null},{"url":null,"slug":"your-instructions-are-not-always-helpful","title":"Your Instructions Are Not Always Helpful: Assessing the Efficacy of Instruction Fine-tuning for Software Vulnerability Detection","date":"2024-01-15","arxiv_id":"2401.07466","repositories_listed":0,"syntology":null},{"url":null,"slug":"distilling-event-sequence-knowledge-from","title":"Distilling Event Sequence Knowledge From Large Language Models","date":"2024-01-14","arxiv_id":"2401.07237","repositories_listed":0,"syntology":null},{"url":null,"slug":"drlc-reinforcement-learning-with-dense","title":"Beyond Sparse Rewards: Enhancing Reinforcement Learning with Language Model Critique in Text Generation","date":"2024-01-14","arxiv_id":"2401.07382","repositories_listed":0,"syntology":null},{"url":null,"slug":"ella-v-stable-neural-codec-language-modeling","title":"ELLA-V: Stable Neural Codec Language Modeling with Alignment-guided Sequence Reordering","date":"2024-01-14","arxiv_id":"2401.07333","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-from-llm-feedback-to","title":"Reinforcement Learning from LLM Feedback to Counteract Goal Misgeneralization","date":"2024-01-14","arxiv_id":"2401.07181","repositories_listed":0,"syntology":null},{"url":null,"slug":"small-language-model-can-self-correct","title":"Small Language Model Can Self-correct","date":"2024-01-14","arxiv_id":"2401.07301","repositories_listed":0,"syntology":null},{"url":null,"slug":"evolving-code-with-a-large-language-model","title":"Evolving Code with A Large Language Model","date":"2024-01-13","arxiv_id":"2401.07102","repositories_listed":0,"syntology":null},{"url":null,"slug":"parameter-efficient-detoxification-with","title":"Parameter-Efficient Detoxification with Contrastive Decoding","date":"2024-01-13","arxiv_id":"2401.06947","repositories_listed":0,"syntology":null},{"url":null,"slug":"tracing-the-genealogies-of-ideas-with-large","title":"Tracing the Genealogies of Ideas with Large Language Model Embeddings","date":"2024-01-13","arxiv_id":"2402.01661","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-systematic-review-of-geospatial-location","title":"A systematic review of geospatial location embedding approaches in large language models: A path to spatial AI systems","date":"2024-01-12","arxiv_id":"2401.10279","repositories_listed":0,"syntology":null},{"url":null,"slug":"dynamic-behaviour-of-connectionist-speech","title":"Dynamic Behaviour of Connectionist Speech Recognition with Strong Latency Constraints","date":"2024-01-12","arxiv_id":"2401.06588","repositories_listed":0,"syntology":null},{"url":null,"slug":"inranker-distilled-rankers-for-zero-shot","title":"InRanker: Distilled Rankers for Zero-shot Information Retrieval","date":"2024-01-12","arxiv_id":"2401.06910","repositories_listed":0,"syntology":null},{"url":null,"slug":"persianmind-a-cross-lingual-persian-english","title":"PersianMind: A Cross-Lingual Persian-English Large Language Model","date":"2024-01-12","arxiv_id":"2401.06466","repositories_listed":0,"syntology":null},{"url":null,"slug":"xls-r-deep-learning-model-for-multilingual","title":"XLS-R Deep Learning Model for Multilingual ASR on Low- Resource Languages: Indonesian, Javanese, and Sundanese","date":"2024-01-12","arxiv_id":"2401.06832","repositories_listed":0,"syntology":null},{"url":null,"slug":"distilling-vision-language-models-on-millions","title":"Distilling Vision-Language Models on Millions of Videos","date":"2024-01-11","arxiv_id":"2401.06129","repositories_listed":0,"syntology":null},{"url":null,"slug":"epilepsyllm-domain-specific-large-language","title":"EpilepsyLLM: Domain-Specific Large Language Model Fine-tuned with Epilepsy Medical Knowledge","date":"2024-01-11","arxiv_id":"2401.05908","repositories_listed":0,"syntology":null},{"url":null,"slug":"how-teachers-can-use-large-language-models","title":"How Teachers Can Use Large Language Models and Bloom's Taxonomy to Create Educational Quizzes","date":"2024-01-11","arxiv_id":"2401.05914","repositories_listed":0,"syntology":null},{"url":null,"slug":"investigating-data-contamination-for-pre","title":"Investigating Data Contamination for Pre-training Language Models","date":"2024-01-11","arxiv_id":"2401.06059","repositories_listed":0,"syntology":null},{"url":null,"slug":"risk-taxonomy-mitigation-and-assessment","title":"Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems","date":"2024-01-11","arxiv_id":"2401.05778","repositories_listed":0,"syntology":null},{"url":null,"slug":"xtrimopglm-unified-100b-scale-pre-trained","title":"xTrimoPGLM: Unified 100B-Scale Pre-trained Transformer for Deciphering the Language of Protein","date":"2024-01-11","arxiv_id":"2401.06199","repositories_listed":0,"syntology":null},{"url":null,"slug":"chatgpt-let-us-chat-sign-language-experiments","title":"ChatGPT, Let us Chat Sign Language: Experiments, Architectural Elements, Challenges and Research Directions","date":"2024-01-10","arxiv_id":"2401.06804","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-classification-of-transversal","title":"Hierarchical Classification of Transversal Skills in Job Ads Based on Sentence Embeddings","date":"2024-01-10","arxiv_id":"2401.05073","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-sharing-in-manufacturing-using","title":"Knowledge Sharing in Manufacturing using Large Language Models: User Evaluation and Model Benchmarking","date":"2024-01-10","arxiv_id":"2401.05200","repositories_listed":0,"syntology":null},{"url":null,"slug":"less-is-more-a-closer-look-at-multi-modal-few","title":"Less is More: A Closer Look at Semantic-based Few-Shot Learning","date":"2024-01-10","arxiv_id":"2401.05010","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-prompt-based-methods-for-zero-shot","title":"Exploring Prompt-Based Methods for Zero-Shot Hypernym Prediction with Large Language Models","date":"2024-01-09","arxiv_id":"2401.04515","repositories_listed":0,"syntology":null},{"url":null,"slug":"how-predictable-is-language-model-benchmark","title":"How predictable is language model benchmark performance?","date":"2024-01-09","arxiv_id":"2401.04757","repositories_listed":0,"syntology":null},{"url":null,"slug":"chain-of-lora-efficient-fine-tuning-of","title":"Chain of LoRA: Efficient Fine-tuning of Language Models via Residual Learning","date":"2024-01-08","arxiv_id":"2401.04151","repositories_listed":0,"syntology":null},{"url":null,"slug":"dme-driver-integrating-human-decision-logic","title":"DME-Driver: Integrating Human Decision Logic and 3D Scene Perception in Autonomous Driving","date":"2024-01-08","arxiv_id":"2401.03641","repositories_listed":0,"syntology":null},{"url":null,"slug":"ffsplit-split-feed-forward-network-for","title":"FFSplit: Split Feed-Forward Network For Optimizing Accuracy-Efficiency Trade-off in Language Model Inference","date":"2024-01-08","arxiv_id":"2401.04044","repositories_listed":0,"syntology":null}],"record_sha256":"a2b61be707cb63cac5a88e1b999d8a94f849f057677651ac36313ef9bb9e2283","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}