{"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/87","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":87,"pages_in_order":142,"rows_per_page":100,"rows":[8601,8700],"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/86","next":"/task/language-modeling/papers/88","papers":[{"url":null,"slug":"multi-modal-retrieval-for-large-language","title":"Multi-Modal Retrieval For Large Language Model Based Speech Recognition","date":"2024-06-13","arxiv_id":"2406.09618","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-effects-of-heterogeneous-data-sources","title":"On the Effects of Heterogeneous Data Sources on Speech-to-Text Foundation Models","date":"2024-06-13","arxiv_id":"2406.09282","repositories_listed":0,"syntology":null},{"url":null,"slug":"rh-sql-refined-schema-and-hardness-prompt-for","title":"RH-SQL: Refined Schema and Hardness Prompt for Text-to-SQL","date":"2024-06-13","arxiv_id":"2406.09133","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-next-era-of-multi-objective","title":"Autonomous Multi-Objective Optimization Using Large Language Model","date":"2024-06-13","arxiv_id":"2406.08987","repositories_listed":0,"syntology":null},{"url":null,"slug":"transformers-meet-neural-algorithmic","title":"Transformers meet Neural Algorithmic Reasoners","date":"2024-06-13","arxiv_id":"2406.09308","repositories_listed":0,"syntology":null},{"url":null,"slug":"unlearning-with-control-assessing-real-world","title":"Unlearning with Control: Assessing Real-world Utility for Large Language Model Unlearning","date":"2024-06-13","arxiv_id":"2406.09179","repositories_listed":0,"syntology":null},{"url":null,"slug":"codecfake-an-initial-dataset-for-detecting","title":"Codecfake: An Initial Dataset for Detecting LLM-based Deepfake Audio","date":"2024-06-12","arxiv_id":"2406.08112","repositories_listed":0,"syntology":null},{"url":null,"slug":"colm-dsr-leveraging-neural-codec-language","title":"CoLM-DSR: Leveraging Neural Codec Language Modeling for Multi-Modal Dysarthric Speech Reconstruction","date":"2024-06-12","arxiv_id":"2406.08336","repositories_listed":0,"syntology":null},{"url":null,"slug":"dualvc-3-leveraging-language-model-generated","title":"DualVC 3: Leveraging Language Model Generated Pseudo Context for End-to-end Low Latency Streaming Voice Conversion","date":"2024-06-12","arxiv_id":"2406.07846","repositories_listed":0,"syntology":null},{"url":null,"slug":"let-s-go-real-talk-spoken-dialogue-model-for","title":"Let's Go Real Talk: Spoken Dialogue Model for Face-to-Face Conversation","date":"2024-06-12","arxiv_id":"2406.07867","repositories_listed":0,"syntology":null},{"url":null,"slug":"memory-is-all-you-need-an-overview-of-compute","title":"Memory Is All You Need: An Overview of Compute-in-Memory Architectures for Accelerating Large Language Model Inference","date":"2024-06-12","arxiv_id":"2406.08413","repositories_listed":0,"syntology":null},{"url":null,"slug":"mobileagentbench-an-efficient-and-user","title":"MobileAgentBench: An Efficient and User-Friendly Benchmark for Mobile LLM Agents","date":"2024-06-12","arxiv_id":"2406.08184","repositories_listed":0,"syntology":null},{"url":null,"slug":"multimodal-representation-loss-between-timed","title":"Multimodal Representation Loss Between Timed Text and Audio for Regularized Speech Separation","date":"2024-06-12","arxiv_id":"2406.08328","repositories_listed":0,"syntology":null},{"url":null,"slug":"olmes-a-standard-for-language-model","title":"OLMES: A Standard for Language Model Evaluations","date":"2024-06-12","arxiv_id":"2406.08446","repositories_listed":0,"syntology":null},{"url":null,"slug":"polyspeech-exploring-unified-multitask-speech","title":"PolySpeech: Exploring Unified Multitask Speech Models for Competitiveness with Single-task Models","date":"2024-06-12","arxiv_id":"2406.07801","repositories_listed":0,"syntology":null},{"url":null,"slug":"real2code-reconstruct-articulated-objects-via","title":"Real2Code: Reconstruct Articulated Objects via Code Generation","date":"2024-06-12","arxiv_id":"2406.08474","repositories_listed":0,"syntology":null},{"url":null,"slug":"short-long-convolutions-help-hardware","title":"Short-Long Convolutions Help Hardware-Efficient Linear Attention to Focus on Long Sequences","date":"2024-06-12","arxiv_id":"2406.08128","repositories_listed":0,"syntology":null},{"url":null,"slug":"supportiveness-based-knowledge-rewriting-for","title":"Supportiveness-based Knowledge Rewriting for Retrieval-augmented Language Modeling","date":"2024-06-12","arxiv_id":"2406.08116","repositories_listed":0,"syntology":null},{"url":null,"slug":"beyond-bare-queries-open-vocabulary-object","title":"Beyond Bare Queries: Open-Vocabulary Object Grounding with 3D Scene Graph","date":"2024-06-11","arxiv_id":"2406.07113","repositories_listed":0,"syntology":null},{"url":null,"slug":"evolving-subnetwork-training-for-large","title":"Evolving Subnetwork Training for Large Language Models","date":"2024-06-11","arxiv_id":"2406.06962","repositories_listed":0,"syntology":null},{"url":null,"slug":"flextron-many-in-one-flexible-large-language","title":"Flextron: Many-in-One Flexible Large Language Model","date":"2024-06-11","arxiv_id":"2406.10260","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-model-empowered-multimodal","title":"Large Language Model-empowered multimodal strain sensory system for shape recognition, monitoring, and human interaction of tensegrity","date":"2024-06-11","arxiv_id":"2406.10264","repositories_listed":0,"syntology":null},{"url":null,"slug":"llamafuzz-large-language-model-enhanced","title":"LLAMAFUZZ: Large Language Model Enhanced Greybox Fuzzing","date":"2024-06-11","arxiv_id":"2406.07714","repositories_listed":0,"syntology":null},{"url":null,"slug":"markov-constraint-as-large-language-model","title":"Markov Constraint as Large Language Model Surrogate","date":"2024-06-11","arxiv_id":"2406.10269","repositories_listed":0,"syntology":null},{"url":null,"slug":"teaching-language-models-to-self-improve-by","title":"Teaching Language Models to Self-Improve by Learning from Language Feedback","date":"2024-06-11","arxiv_id":"2406.07168","repositories_listed":0,"syntology":null},{"url":null,"slug":"ternaryllm-ternarized-large-language-model","title":"TernaryLLM: Ternarized Large Language Model","date":"2024-06-11","arxiv_id":"2406.07177","repositories_listed":0,"syntology":null},{"url":null,"slug":"world-models-with-hints-of-large-language","title":"World Models with Hints of Large Language Models for Goal Achieving","date":"2024-06-11","arxiv_id":"2406.07381","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-large-language-model-pipeline-for-breast","title":"A Large Language Model Pipeline for Breast Cancer Oncology","date":"2024-06-10","arxiv_id":"2406.06455","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-a-personal-health-large-language","title":"Towards a Personal Health Large Language Model","date":"2024-06-10","arxiv_id":"2406.06474","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-signal-processing-in-large-language","title":"Towards Signal Processing In Large Language Models","date":"2024-06-10","arxiv_id":"2406.10254","repositories_listed":0,"syntology":null},{"url":null,"slug":"transforming-wearable-data-into-health","title":"Transforming Wearable Data into Health Insights using Large Language Model Agents","date":"2024-06-10","arxiv_id":"2406.06464","repositories_listed":0,"syntology":null},{"url":null,"slug":"tx-llm-a-large-language-model-for","title":"Tx-LLM: A Large Language Model for Therapeutics","date":"2024-06-10","arxiv_id":"2406.06316","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-knowledge-component-based-methodology-for","title":"A Knowledge-Component-Based Methodology for Evaluating AI Assistants","date":"2024-06-09","arxiv_id":"2406.05603","repositories_listed":0,"syntology":null},{"url":null,"slug":"digital-business-model-analysis-using-a-large","title":"Digital Business Model Analysis Using a Large Language Model","date":"2024-06-09","arxiv_id":"2406.05741","repositories_listed":0,"syntology":null},{"url":null,"slug":"llm-questionnaire-completion-for-automatic","title":"LLM Questionnaire Completion for Automatic Psychiatric Assessment","date":"2024-06-09","arxiv_id":"2406.06636","repositories_listed":0,"syntology":null},{"url":null,"slug":"text-aware-and-context-aware-expressive","title":"Text-aware and Context-aware Expressive Audiobook Speech Synthesis","date":"2024-06-09","arxiv_id":"2406.05672","repositories_listed":0,"syntology":null},{"url":null,"slug":"aligning-human-knowledge-with-visual-concepts","title":"Aligning Human Knowledge with Visual Concepts Towards Explainable Medical Image Classification","date":"2024-06-08","arxiv_id":"2406.05596","repositories_listed":0,"syntology":null},{"url":null,"slug":"deconstructing-the-ethics-of-large-language","title":"Deconstructing The Ethics of Large Language Models from Long-standing Issues to New-emerging Dilemmas: A Survey","date":"2024-06-08","arxiv_id":"2406.05392","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-the-benefits-of-tokenization-of","title":"Exploring the Benefits of Tokenization of Discrete Acoustic Units","date":"2024-06-08","arxiv_id":"2406.05547","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-language-model-guided-framework-for-mining","title":"A Language Model-Guided Framework for Mining Time Series with Distributional Shifts","date":"2024-06-07","arxiv_id":"2406.05249","repositories_listed":0,"syntology":null},{"url":null,"slug":"accelerating-evolutionary-exploration-through","title":"Accelerating evolutionary exploration through language model-based transfer learning","date":"2024-06-07","arxiv_id":"2406.05166","repositories_listed":0,"syntology":null},{"url":null,"slug":"boosting-diffusion-model-for-spectrogram-up","title":"Boosting Diffusion Model for Spectrogram Up-sampling in Text-to-speech: An Empirical Study","date":"2024-06-07","arxiv_id":"2406.04633","repositories_listed":0,"syntology":null},{"url":null,"slug":"chatpcg-large-language-model-driven-reward","title":"ChatPCG: Large Language Model-Driven Reward Design for Procedural Content Generation","date":"2024-06-07","arxiv_id":"2406.11875","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-model-guided-document","title":"Large Language Model-guided Document Selection","date":"2024-06-07","arxiv_id":"2406.04638","repositories_listed":0,"syntology":null},{"url":null,"slug":"matter-memory-augmented-transformer-using","title":"MATTER: Memory-Augmented Transformer Using Heterogeneous Knowledge Sources","date":"2024-06-07","arxiv_id":"2406.04670","repositories_listed":0,"syntology":null},{"url":null,"slug":"quantifying-geospatial-in-the-common-crawl","title":"Quantifying Geospatial in the Common Crawl Corpus","date":"2024-06-07","arxiv_id":"2406.04952","repositories_listed":0,"syntology":null},{"url":null,"slug":"uncertainty-aware-learning-for-language-model","title":"Uncertainty Aware Learning for Language Model Alignment","date":"2024-06-07","arxiv_id":"2406.04854","repositories_listed":0,"syntology":null},{"url":null,"slug":"are-large-language-models-the-new-interface","title":"Are Large Language Models the New Interface for Data Pipelines?","date":"2024-06-06","arxiv_id":"2406.06596","repositories_listed":0,"syntology":null},{"url":null,"slug":"bindgpt-a-scalable-framework-for-3d-molecular","title":"BindGPT: A Scalable Framework for 3D Molecular Design via Language Modeling and Reinforcement Learning","date":"2024-06-06","arxiv_id":"2406.03686","repositories_listed":0,"syntology":null},{"url":null,"slug":"confabulation-the-surprising-value-of-large","title":"Confabulation: The Surprising Value of Large Language Model Hallucinations","date":"2024-06-06","arxiv_id":"2406.04175","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-audio-codec-based-zero-shot-text-to","title":"Improving Audio Codec-based Zero-Shot Text-to-Speech Synthesis with Multi-Modal Context and Large Language Model","date":"2024-06-06","arxiv_id":"2406.03706","repositories_listed":0,"syntology":null},{"url":null,"slug":"llplace-the-3d-indoor-scene-layout-generation","title":"LLplace: The 3D Indoor Scene Layout Generation and Editing via Large Language Model","date":"2024-06-06","arxiv_id":"2406.03866","repositories_listed":0,"syntology":null},{"url":null,"slug":"stratified-prediction-powered-inference-for","title":"Stratified Prediction-Powered Inference for Hybrid Language Model Evaluation","date":"2024-06-06","arxiv_id":"2406.04291","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-understanding-task-agnostic-debiasing","title":"Towards Understanding Task-agnostic Debiasing Through the Lenses of Intrinsic Bias and Forgetfulness","date":"2024-06-06","arxiv_id":"2406.04146","repositories_listed":0,"syntology":null},{"url":null,"slug":"what-languages-are-easy-to-language-model-a","title":"What Languages are Easy to Language-Model? A Perspective from Learning Probabilistic Regular Languages","date":"2024-06-06","arxiv_id":"2406.04289","repositories_listed":0,"syntology":null},{"url":null,"slug":"does-your-data-spark-joy-performance-gains","title":"Does your data spark joy? Performance gains from domain upsampling at the end of training","date":"2024-06-05","arxiv_id":"2406.03476","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-robustness-in-doctor-patient","title":"Exploring Robustness in Doctor-Patient Conversation Summarization: An Analysis of Out-of-Domain SOAP Notes","date":"2024-06-05","arxiv_id":"2406.02826","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-tarzan-to-tolkien-controlling-the","title":"From Tarzan to Tolkien: Controlling the Language Proficiency Level of LLMs for Content Generation","date":"2024-06-05","arxiv_id":"2406.03030","repositories_listed":0,"syntology":null},{"url":null,"slug":"item-language-model-for-conversational","title":"Item-Language Model for Conversational Recommendation","date":"2024-06-05","arxiv_id":"2406.02844","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-infused-legal-wisdom-navigating-llm","title":"Knowledge-Infused Legal Wisdom: Navigating LLM Consultation through the Lens of Diagnostics and Positive-Unlabeled Reinforcement Learning","date":"2024-06-05","arxiv_id":"2406.03600","repositories_listed":0,"syntology":null},{"url":null,"slug":"language-model-can-do-knowledge-tracing","title":"Language Model Can Do Knowledge Tracing: Simple but Effective Method to Integrate Language Model and Knowledge Tracing Task","date":"2024-06-05","arxiv_id":"2406.02893","repositories_listed":0,"syntology":null},{"url":null,"slug":"plad-preference-based-large-language-model","title":"PLaD: Preference-based Large Language Model Distillation with Pseudo-Preference Pairs","date":"2024-06-05","arxiv_id":"2406.02886","repositories_listed":0,"syntology":null},{"url":null,"slug":"radbartsum-domain-specific-adaption-of","title":"RadBARTsum: Domain Specific Adaption of Denoising Sequence-to-Sequence Models for Abstractive Radiology Report Summarization","date":"2024-06-05","arxiv_id":"2406.03062","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-independence-promoting-loss-for-music","title":"An Independence-promoting Loss for Music Generation with Language Models","date":"2024-06-04","arxiv_id":"2406.02315","repositories_listed":0,"syntology":null},{"url":null,"slug":"assessing-the-performance-of-chinese-open","title":"Assessing the Performance of Chinese Open Source Large Language Models in Information Extraction Tasks","date":"2024-06-04","arxiv_id":"2406.02079","repositories_listed":0,"syntology":null},{"url":null,"slug":"discrete-multimodal-transformers-with-a","title":"Discrete Multimodal Transformers with a Pretrained Large Language Model for Mixed-Supervision Speech Processing","date":"2024-06-04","arxiv_id":"2406.06582","repositories_listed":0,"syntology":null},{"url":null,"slug":"disentangling-logic-the-role-of-context-in","title":"Disentangling Logic: The Role of Context in Large Language Model Reasoning Capabilities","date":"2024-06-04","arxiv_id":"2406.02787","repositories_listed":0,"syntology":null},{"url":null,"slug":"diver-large-language-model-decoding-with-span","title":"Diver: Large Language Model Decoding with Span-Level Mutual Information Verification","date":"2024-06-04","arxiv_id":"2406.02120","repositories_listed":0,"syntology":null},{"url":null,"slug":"dreureka-language-model-guided-sim-to-real","title":"DrEureka: Language Model Guided Sim-To-Real Transfer","date":"2024-06-04","arxiv_id":"2406.01967","repositories_listed":0,"syntology":null},{"url":null,"slug":"edit-distance-robust-watermarks-for-language","title":"Edit Distance Robust Watermarks via Indexing Pseudorandom Codes","date":"2024-06-04","arxiv_id":"2406.02633","repositories_listed":0,"syntology":null},{"url":null,"slug":"honeygpt-breaking-the-trilemma-in-terminal","title":"HoneyGPT: Breaking the Trilemma in Terminal Honeypots with Large Language Model","date":"2024-06-04","arxiv_id":"2406.01882","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-model-enabled-multi-agent","title":"Large Language Model-Enabled Multi-Agent Manufacturing Systems","date":"2024-06-04","arxiv_id":"2406.01893","repositories_listed":0,"syntology":null},{"url":null,"slug":"longssm-on-the-length-extension-of-state","title":"LongSSM: On the Length Extension of State-space Models in Language Modelling","date":"2024-06-04","arxiv_id":"2406.02080","repositories_listed":0,"syntology":null},{"url":null,"slug":"masksr-masked-language-model-for-full-band","title":"MaskSR: Masked Language Model for Full-band Speech Restoration","date":"2024-06-04","arxiv_id":"2406.02092","repositories_listed":0,"syntology":null},{"url":null,"slug":"meta-designing-quantum-experiments-with","title":"Meta-Designing Quantum Experiments with Language Models","date":"2024-06-04","arxiv_id":"2406.02470","repositories_listed":0,"syntology":null},{"url":null,"slug":"occamllm-fast-and-exact-language-model","title":"OccamLLM: Fast and Exact Language Model Arithmetic in a Single Step","date":"2024-06-04","arxiv_id":"2406.06576","repositories_listed":0,"syntology":null},{"url":null,"slug":"phonetic-enhanced-language-modeling-for-text","title":"Phonetic Enhanced Language Modeling for Text-to-Speech Synthesis","date":"2024-06-04","arxiv_id":"2406.02009","repositories_listed":0,"syntology":null},{"url":null,"slug":"radar-spectra-language-model-for-automotive","title":"Radar Spectra-Language Model for Automotive Scene Parsing","date":"2024-06-04","arxiv_id":"2406.02158","repositories_listed":0,"syntology":null},{"url":null,"slug":"rkld-reverse-kl-divergence-based-knowledge","title":"RKLD: Reverse KL-Divergence-based Knowledge Distillation for Unlearning Personal Information in Large Language Models","date":"2024-06-04","arxiv_id":"2406.01983","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-supervised-singing-voice-pre-training","title":"Self-Supervised Singing Voice Pre-Training towards Speech-to-Singing Conversion","date":"2024-06-04","arxiv_id":"2406.02429","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-effective-time-aware-language","title":"Towards Effective Time-Aware Language Representation: Exploring Enhanced Temporal Understanding in Language Models","date":"2024-06-04","arxiv_id":"2406.01863","repositories_listed":0,"syntology":null},{"url":null,"slug":"why-would-you-suggest-that-human-trust-in","title":"Why Would You Suggest That? Human Trust in Language Model Responses","date":"2024-06-04","arxiv_id":"2406.02018","repositories_listed":0,"syntology":null},{"url":null,"slug":"asynchronous-multi-server-federated-learning","title":"Asynchronous Multi-Server Federated Learning for Geo-Distributed Clients","date":"2024-06-03","arxiv_id":"2406.01439","repositories_listed":0,"syntology":null},{"url":null,"slug":"ed-sam-an-efficient-diffusion-sampling","title":"ED-SAM: An Efficient Diffusion Sampling Approach to Domain Generalization in Vision-Language Foundation Models","date":"2024-06-03","arxiv_id":"2406.01432","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-model-assisted-optimal-bidding","title":"Large Language Model Assisted Optimal Bidding of BESS in FCAS Market: An AI-agent based Approach","date":"2024-06-03","arxiv_id":"2406.00974","repositories_listed":0,"syntology":null},{"url":null,"slug":"llm-and-gnn-are-complementary-distilling-llm","title":"LLM and GNN are Complementary: Distilling LLM for Multimodal Graph Learning","date":"2024-06-03","arxiv_id":"2406.01032","repositories_listed":0,"syntology":null},{"url":null,"slug":"luna-an-evaluation-foundation-model-to-catch","title":"Luna: An Evaluation Foundation Model to Catch Language Model Hallucinations with High Accuracy and Low Cost","date":"2024-06-03","arxiv_id":"2406.00975","repositories_listed":0,"syntology":null},{"url":null,"slug":"olora-orthonormal-low-rank-adaptation-of","title":"OLoRA: Orthonormal Low-Rank Adaptation of Large Language Models","date":"2024-06-03","arxiv_id":"2406.01775","repositories_listed":0,"syntology":null},{"url":null,"slug":"scalable-ensembling-for-mitigating-reward","title":"Scalable Ensembling For Mitigating Reward Overoptimisation","date":"2024-06-03","arxiv_id":"2406.01013","repositories_listed":0,"syntology":null},{"url":null,"slug":"superhuman-performance-in-urology-board","title":"Superhuman performance in urology board questions by an explainable large language model enabled for context integration of the European Association of Urology guidelines: the UroBot study","date":"2024-06-03","arxiv_id":"2406.01428","repositories_listed":0,"syntology":null},{"url":null,"slug":"understanding-token-probability-encoding-in","title":"Understanding Token Probability Encoding in Output Embeddings","date":"2024-06-03","arxiv_id":"2406.01468","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-distractor-generation-via-large","title":"Unsupervised Distractor Generation via Large Language Model Distilling and Counterfactual Contrastive Decoding","date":"2024-06-03","arxiv_id":"2406.01306","repositories_listed":0,"syntology":null},{"url":null,"slug":"distortion-free-watermarks-are-not-truly","title":"Distortion-free Watermarks are not Truly Distortion-free under Watermark Key Collisions","date":"2024-06-02","arxiv_id":"2406.02603","repositories_listed":0,"syntology":null},{"url":null,"slug":"harnessing-business-and-media-insights-with","title":"Harnessing Business and Media Insights with Large Language Models","date":"2024-06-02","arxiv_id":"2406.06559","repositories_listed":0,"syntology":null},{"url":null,"slug":"longskywork-a-training-recipe-for-efficiently","title":"LongSkywork: A Training Recipe for Efficiently Extending Context Length in Large Language Models","date":"2024-06-02","arxiv_id":"2406.00605","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-a-copilot-in-bim-authoring-tool-using","title":"Towards a copilot in BIM authoring tool using a large language model-based agent for intelligent human-machine interaction","date":"2024-06-02","arxiv_id":"2406.16903","repositories_listed":0,"syntology":null},{"url":null,"slug":"controlling-large-language-model-agents-with","title":"Controlling Large Language Model Agents with Entropic Activation Steering","date":"2024-06-01","arxiv_id":"2406.00244","repositories_listed":0,"syntology":null},{"url":null,"slug":"henasy-learning-to-assemble-scene-entities","title":"HENASY: Learning to Assemble Scene-Entities for Egocentric Video-Language Model","date":"2024-06-01","arxiv_id":"2406.00307","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-model-confidence-estimation","title":"Large Language Model Confidence Estimation via Black-Box Access","date":"2024-06-01","arxiv_id":"2406.04370","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-overcoming-miscalibrated-conversational","title":"On Overcoming Miscalibrated Conversational Priors in LLM-based Chatbots","date":"2024-06-01","arxiv_id":"2406.01633","repositories_listed":0,"syntology":null}],"record_sha256":"5d3590d428e24963e3545d703760778f46cc6619c12a585030bf9aa13fae6c62","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}