{"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-modelling/papers/95","list_of":"/task/language-modelling","task":"Language Modelling","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":95,"pages_in_order":177,"rows_per_page":100,"rows":[9401,9500],"of":17610,"counts":{"archive_papers_tagged":17610,"with_a_code_link":7012,"where_syntology_ran_a_sample":2428,"not_listed_spam_title":0,"listed":17610,"listed_where_code_ran":2428,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2027,"every_run_a_failure_of_syntologys_instrument":401,"listed_with_a_run_with_no_instrument_failure":2027,"listed_every_run_a_failure_of_syntologys_instrument":401,"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-modelling","prev":"/task/language-modelling/papers/94","next":"/task/language-modelling/papers/96","papers":[{"url":null,"slug":"multi-modal-generative-ai-multi-modal-llm","title":"Multi-Modal Generative AI: Multi-modal LLM, Diffusion and Beyond","date":"2024-09-23","arxiv_id":"2409.14993","repositories_listed":0,"syntology":null},{"url":null,"slug":"pre-trained-language-model-and-knowledge","title":"Pre-trained Language Model and Knowledge Distillation for Lightweight Sequential Recommendation","date":"2024-09-23","arxiv_id":"2409.14810","repositories_listed":0,"syntology":null},{"url":null,"slug":"racer-rich-language-guided-failure-recovery","title":"RACER: Rich Language-Guided Failure Recovery Policies for Imitation Learning","date":"2024-09-23","arxiv_id":"2409.14674","repositories_listed":0,"syntology":null},{"url":null,"slug":"rethinking-conventional-wisdom-in-machine","title":"Rethinking Conventional Wisdom in Machine Learning: From Generalization to Scaling","date":"2024-09-23","arxiv_id":"2409.15156","repositories_listed":0,"syntology":null},{"url":null,"slug":"target-aware-language-modeling-via-granular","title":"Target-Aware Language Modeling via Granular Data Sampling","date":"2024-09-23","arxiv_id":"2409.14705","repositories_listed":0,"syntology":null},{"url":null,"slug":"vlmine-long-tail-data-mining-with-vision","title":"VLMine: Long-Tail Data Mining with Vision Language Models","date":"2024-09-23","arxiv_id":"2409.15486","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-large-language-model-and-denoising","title":"A Large Language Model and Denoising Diffusion Framework for Targeted Design of Microstructures with Commands in Natural Language","date":"2024-09-22","arxiv_id":"2409.14473","repositories_listed":0,"syntology":null},{"url":null,"slug":"backtracking-improves-generation-safety","title":"Backtracking Improves Generation Safety","date":"2024-09-22","arxiv_id":"2409.14586","repositories_listed":0,"syntology":null},{"url":null,"slug":"2409-13972","title":"Can Language Model Understand Word Semantics as A Chatbot? An Empirical Study of Language Model Internal External Mismatch","date":"2024-09-21","arxiv_id":"2409.13972","repositories_listed":0,"syntology":null},{"url":null,"slug":"2409-13979","title":"Role-Play Paradox in Large Language Models: Reasoning Performance Gains and Ethical Dilemmas","date":"2024-09-21","arxiv_id":"2409.13979","repositories_listed":0,"syntology":null},{"url":null,"slug":"2409-14097","title":"Probing Context Localization of Polysemous Words in Pre-trained Language Model Sub-Layers","date":"2024-09-21","arxiv_id":"2409.14097","repositories_listed":0,"syntology":null},{"url":null,"slug":"2409-14200","title":"Data-centric NLP Backdoor Defense from the Lens of Memorization","date":"2024-09-21","arxiv_id":"2409.14200","repositories_listed":0,"syntology":null},{"url":null,"slug":"echo-environmental-sound-classification-with","title":"ECHO: Environmental Sound Classification with Hierarchical Ontology-guided Semi-Supervised Learning","date":"2024-09-21","arxiv_id":"2409.14043","repositories_listed":0,"syntology":null},{"url":"/paper/loop-residual-neural-networks-for-iterative","slug":"loop-residual-neural-networks-for-iterative","title":"Loop Neural Networks for Parameter Sharing","date":"2024-09-21","arxiv_id":"2409.14199","repositories_listed":0,"syntology":null},{"url":null,"slug":"oaei-llm-a-benchmark-dataset-for","title":"OAEI-LLM: A Benchmark Dataset for Understanding Large Language Model Hallucinations in Ontology Matching","date":"2024-09-21","arxiv_id":"2409.14038","repositories_listed":0,"syntology":null},{"url":null,"slug":"test-time-learning-for-time-series","title":"Test Time Learning for Time Series Forecasting","date":"2024-09-21","arxiv_id":"2409.14012","repositories_listed":0,"syntology":null},{"url":null,"slug":"will-large-language-models-be-a-panacea-to","title":"A Survey on Large Language Model-empowered Autonomous Driving","date":"2024-09-21","arxiv_id":"2409.14165","repositories_listed":0,"syntology":null},{"url":null,"slug":"ci-bench-benchmarking-contextual-integrity-of","title":"CI-Bench: Benchmarking Contextual Integrity of AI Assistants on Synthetic Data","date":"2024-09-20","arxiv_id":"2409.13903","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-scaling-laws-for-local-sgd-in-large","title":"Exploring Scaling Laws for Local SGD in Large Language Model Training","date":"2024-09-20","arxiv_id":"2409.13198","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-model-should-understand-pinyin","title":"Large Language Model Should Understand Pinyin for Chinese ASR Error Correction","date":"2024-09-20","arxiv_id":"2409.13262","repositories_listed":0,"syntology":null},{"url":null,"slug":"lm-assisted-keyword-biasing-with-aho-corasick","title":"LM-assisted keyword biasing with Aho-Corasick algorithm for Transducer-based ASR","date":"2024-09-20","arxiv_id":"2409.13514","repositories_listed":0,"syntology":null},{"url":null,"slug":"prompting-large-language-models-for-1","title":"Prompting Large Language Models for Supporting the Differential Diagnosis of Anemia","date":"2024-09-20","arxiv_id":"2409.15377","repositories_listed":0,"syntology":null},{"url":null,"slug":"fine-tuning-large-language-models-for-4","title":"Fine Tuning Large Language Models for Medicine: The Role and Importance of Direct Preference Optimization","date":"2024-09-19","arxiv_id":"2409.12741","repositories_listed":0,"syntology":null},{"url":null,"slug":"foodpuzzle-developing-large-language-model","title":"FoodPuzzle: Developing Large Language Model Agents as Flavor Scientists","date":"2024-09-19","arxiv_id":"2409.12832","repositories_listed":0,"syntology":null},{"url":null,"slug":"incremental-and-data-efficient-concept","title":"Incremental and Data-Efficient Concept Formation to Support Masked Word Prediction","date":"2024-09-19","arxiv_id":"2409.12440","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowformer-revisiting-transformers-for","title":"KnowFormer: Revisiting Transformers for Knowledge Graph Reasoning","date":"2024-09-19","arxiv_id":"2409.12865","repositories_listed":0,"syntology":null},{"url":null,"slug":"lare-latent-augmentation-using-regional","title":"LARE: Latent Augmentation using Regional Embedding with Vision-Language Model","date":"2024-09-19","arxiv_id":"2409.12597","repositories_listed":0,"syntology":null},{"url":null,"slug":"llmr-knowledge-distillation-with-a-large","title":"LLMR: Knowledge Distillation with a Large Language Model-Induced Reward","date":"2024-09-19","arxiv_id":"2409.12500","repositories_listed":0,"syntology":null},{"url":null,"slug":"michelangelo-long-context-evaluations-beyond","title":"Michelangelo: Long Context Evaluations Beyond Haystacks via Latent Structure Queries","date":"2024-09-19","arxiv_id":"2409.12640","repositories_listed":0,"syntology":null},{"url":null,"slug":"personaflow-boosting-research-ideation-with","title":"PersonaFlow: Boosting Research Ideation with LLM-Simulated Expert Personas","date":"2024-09-19","arxiv_id":"2409.12538","repositories_listed":0,"syntology":null},{"url":null,"slug":"preference-alignment-improves-language-model","title":"Preference Alignment Improves Language Model-Based TTS","date":"2024-09-19","arxiv_id":"2409.12403","repositories_listed":0,"syntology":null},{"url":null,"slug":"small-language-models-are-equation-reasoners","title":"Small Language Models are Equation Reasoners","date":"2024-09-19","arxiv_id":"2409.12393","repositories_listed":0,"syntology":null},{"url":null,"slug":"dual-layer-training-and-decoding-of-large","title":"MeTHanol: Modularized Thinking Language Models with Intermediate Layer Thinking, Decoding and Bootstrapping Reasoning","date":"2024-09-18","arxiv_id":"2409.12059","repositories_listed":0,"syntology":null},{"url":null,"slug":"flare-fusing-language-models-and","title":"FLARE: Fusing Language Models and Collaborative Architectures for Recommender Enhancement","date":"2024-09-18","arxiv_id":"2409.11699","repositories_listed":0,"syntology":null},{"url":null,"slug":"grin-gradient-informed-moe","title":"GRIN: GRadient-INformed MoE","date":"2024-09-18","arxiv_id":"2409.12136","repositories_listed":0,"syntology":null},{"url":null,"slug":"llms-persona-plug-personalized-llms","title":"LLMs + Persona-Plug = Personalized LLMs","date":"2024-09-18","arxiv_id":"2409.11901","repositories_listed":0,"syntology":null},{"url":null,"slug":"low-frame-rate-speech-codec-a-codec-designed","title":"Low Frame-rate Speech Codec: a Codec Designed for Fast High-quality Speech LLM Training and Inference","date":"2024-09-18","arxiv_id":"2409.12117","repositories_listed":0,"syntology":null},{"url":null,"slug":"takin-a-cohort-of-superior-quality-zero-shot","title":"Takin: A Cohort of Superior Quality Zero-shot Speech Generation Models","date":"2024-09-18","arxiv_id":"2409.12139","repositories_listed":0,"syntology":null},{"url":null,"slug":"vera-validation-and-enhancement-for-retrieval","title":"VERA: Validation and Enhancement for Retrieval Augmented systems","date":"2024-09-18","arxiv_id":"2409.15364","repositories_listed":0,"syntology":null},{"url":null,"slug":"bio-inspired-mamba-temporal-locality-and","title":"Bio-Inspired Mamba: Temporal Locality and Bioplausible Learning in Selective State Space Models","date":"2024-09-17","arxiv_id":"2409.11263","repositories_listed":0,"syntology":null},{"url":null,"slug":"challenging-fairness-a-comprehensive","title":"Unveiling and Mitigating Bias in Large Language Model Recommendations: A Path to Fairness","date":"2024-09-17","arxiv_id":"2409.10825","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-chatgpt-based-augmentation","title":"Exploring ChatGPT-based Augmentation Strategies for Contrastive Aspect-based Sentiment Analysis","date":"2024-09-17","arxiv_id":"2409.11218","repositories_listed":0,"syntology":null},{"url":null,"slug":"llm-as-a-judge-reward-model-what-they-can-and","title":"LLM-as-a-Judge & Reward Model: What They Can and Cannot Do","date":"2024-09-17","arxiv_id":"2409.11239","repositories_listed":0,"syntology":null},{"url":null,"slug":"proslm-a-prolog-synergized-language-model-for","title":"ProSLM : A Prolog Synergized Language Model for explainable Domain Specific Knowledge Based Question Answering","date":"2024-09-17","arxiv_id":"2409.11589","repositories_listed":0,"syntology":null},{"url":null,"slug":"says-who-effective-zero-shot-annotation-of","title":"Says Who? Effective Zero-Shot Annotation of Focalization","date":"2024-09-17","arxiv_id":"2409.11390","repositories_listed":0,"syntology":null},{"url":null,"slug":"semformer-transformer-language-models-with","title":"Semformer: Transformer Language Models with Semantic Planning","date":"2024-09-17","arxiv_id":"2409.11143","repositories_listed":0,"syntology":null},{"url":null,"slug":"strategic-insights-in-human-and-large","title":"Strategic Insights in Human and Large Language Model Tactics at Word Guessing Games","date":"2024-09-17","arxiv_id":"2409.11112","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-novel-malicious-packet-recognition-a","title":"Towards Novel Malicious Packet Recognition: A Few-Shot Learning Approach","date":"2024-09-17","arxiv_id":"2409.11254","repositories_listed":0,"syntology":null},{"url":null,"slug":"lab-ai-retrieval-augmented-language-model-for","title":"Lab-AI: Using Retrieval Augmentation to Enhance Language Models for Personalized Lab Test Interpretation in Clinical Medicine","date":"2024-09-16","arxiv_id":"2409.18986","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-model-enhanced-hard-sample","title":"Large Language Model Enhanced Hard Sample Identification for Denoising Recommendation","date":"2024-09-16","arxiv_id":"2409.10343","repositories_listed":0,"syntology":null},{"url":null,"slug":"multidimensional-human-activity-recognition","title":"Multidimensional Human Activity Recognition With Large Language Model: A Conceptual Framework","date":"2024-09-16","arxiv_id":"2410.03546","repositories_listed":0,"syntology":null},{"url":null,"slug":"neusis-a-compositional-neuro-symbolic","title":"NEUSIS: A Compositional Neuro-Symbolic Framework for Autonomous Perception, Reasoning, and Planning in Complex UAV Search Missions","date":"2024-09-16","arxiv_id":"2409.10196","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-control-with-human-like-reasoning","title":"Automatic Control With Human-Like Reasoning: Exploring Language Model Embodied Air Traffic Agents","date":"2024-09-15","arxiv_id":"2409.09717","repositories_listed":0,"syntology":null},{"url":null,"slug":"causal-inference-with-large-language-model-a","title":"Causal Inference with Large Language Model: A Survey","date":"2024-09-15","arxiv_id":"2409.09822","repositories_listed":0,"syntology":null},{"url":null,"slug":"elmi-interactive-and-intelligent-sign","title":"ELMI: Interactive and Intelligent Sign Language Translation of Lyrics for Song Signing","date":"2024-09-15","arxiv_id":"2409.09760","repositories_listed":0,"syntology":null},{"url":null,"slug":"gp-gpt-large-language-model-for-gene","title":"GP-GPT: Large Language Model for Gene-Phenotype Mapping","date":"2024-09-15","arxiv_id":"2409.09825","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-model-based-generative-error","title":"Large Language Model Based Generative Error Correction: A Challenge and Baselines for Speech Recognition, Speaker Tagging, and Emotion Recognition","date":"2024-09-15","arxiv_id":"2409.09785","repositories_listed":0,"syntology":null},{"url":null,"slug":"nevlp-noise-robust-framework-for-efficient","title":"NEVLP: Noise-Robust Framework for Efficient Vision-Language Pre-training","date":"2024-09-15","arxiv_id":"2409.09582","repositories_listed":0,"syntology":null},{"url":null,"slug":"recent-advances-in-deep-learning-and-language","title":"Recent advances in deep learning and language models for studying the microbiome","date":"2024-09-15","arxiv_id":"2409.10579","repositories_listed":0,"syntology":null},{"url":null,"slug":"rethinking-kenlm-good-and-bad-model-ensembles","title":"Rethinking KenLM: Good and Bad Model Ensembles for Efficient Text Quality Filtering in Large Web Corpora","date":"2024-09-15","arxiv_id":"2409.09613","repositories_listed":0,"syntology":null},{"url":null,"slug":"tg-llava-text-guided-llava-via-learnable","title":"TG-LLaVA: Text Guided LLaVA via Learnable Latent Embeddings","date":"2024-09-15","arxiv_id":"2409.09564","repositories_listed":0,"syntology":null},{"url":null,"slug":"autoregressive-chain-of-thought-cot-simeq","title":"Autoregressive + Chain of Thought = Recurrent: Recurrence's Role in Language Models' Computability and a Revisit of Recurrent Transformer","date":"2024-09-14","arxiv_id":"2409.09239","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-fine-tuning-of-large-language","title":"Efficient Fine-Tuning of Large Language Models for Automated Medical Documentation","date":"2024-09-14","arxiv_id":"2409.09324","repositories_listed":0,"syntology":null},{"url":null,"slug":"infrared-and-visible-image-fusion-with-1","title":"Infrared and Visible Image Fusion with Hierarchical Human Perception","date":"2024-09-14","arxiv_id":"2409.09291","repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-semantic-knowledge-distillation-and","title":"Joint Semantic Knowledge Distillation and Masked Acoustic Modeling for Full-band Speech Restoration with Improved Intelligibility","date":"2024-09-14","arxiv_id":"2409.09357","repositories_listed":0,"syntology":null},{"url":null,"slug":"language-models-grok-to-copy","title":"Language Models \"Grok\" to Copy","date":"2024-09-14","arxiv_id":"2409.09281","repositories_listed":0,"syntology":null},{"url":null,"slug":"language-queried-target-sound-extraction","title":"Language-Queried Target Sound Extraction Without Parallel Training Data","date":"2024-09-14","arxiv_id":"2409.09398","repositories_listed":0,"syntology":null},{"url":null,"slug":"overcoming-linguistic-barriers-in-code","title":"Overcoming linguistic barriers in code assistants: creating a QLoRA adapter to improve support for Russian-language code writing instructions","date":"2024-09-14","arxiv_id":"2409.09353","repositories_listed":0,"syntology":null},{"url":null,"slug":"see-semantically-aligned-eeg-to-text","title":"SEE: Semantically Aligned EEG-to-Text Translation","date":"2024-09-14","arxiv_id":"2409.16312","repositories_listed":0,"syntology":null},{"url":null,"slug":"atflrec-a-multimodal-recommender-system-with","title":"ATFLRec: A Multimodal Recommender System with Audio-Text Fusion and Low-Rank Adaptation via Instruction-Tuned Large Language Model","date":"2024-09-13","arxiv_id":"2409.08543","repositories_listed":0,"syntology":null},{"url":null,"slug":"contri-e-ve-context-retrieve-for-scholarly","title":"Contri(e)ve: Context + Retrieve for Scholarly Question Answering","date":"2024-09-13","arxiv_id":"2409.09010","repositories_listed":0,"syntology":null},{"url":null,"slug":"eir-thai-medical-large-language-models","title":"Eir: Thai Medical Large Language Models","date":"2024-09-13","arxiv_id":"2409.08523","repositories_listed":0,"syntology":null},{"url":null,"slug":"electrocardiogram-report-generation-and","title":"Electrocardiogram Report Generation and Question Answering via Retrieval-Augmented Self-Supervised Modeling","date":"2024-09-13","arxiv_id":"2409.08788","repositories_listed":0,"syntology":null},{"url":null,"slug":"expediting-and-elevating-large-language-model","title":"Expediting and Elevating Large Language Model Reasoning via Hidden Chain-of-Thought Decoding","date":"2024-09-13","arxiv_id":"2409.08561","repositories_listed":0,"syntology":null},{"url":null,"slug":"mutual-theory-of-mind-in-human-ai","title":"Mutual Theory of Mind in Human-AI Collaboration: An Empirical Study with LLM-driven AI Agents in a Real-time Shared Workspace Task","date":"2024-09-13","arxiv_id":"2409.08811","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-unified-facial-action-unit","title":"Towards Unified Facial Action Unit Recognition Framework by Large Language Models","date":"2024-09-13","arxiv_id":"2409.08444","repositories_listed":0,"syntology":null},{"url":null,"slug":"winning-solution-for-meta-kdd-cup-24","title":"Winning Solution For Meta KDD Cup' 24","date":"2024-09-13","arxiv_id":"2410.00005","repositories_listed":0,"syntology":null},{"url":null,"slug":"early-joint-learning-of-emotion-information","title":"Early Joint Learning of Emotion Information Makes MultiModal Model Understand You Better","date":"2024-09-12","arxiv_id":"2409.18971","repositories_listed":0,"syntology":null},{"url":null,"slug":"full-text-error-correction-for-chinese-speech","title":"Full-text Error Correction for Chinese Speech Recognition with Large Language Model","date":"2024-09-12","arxiv_id":"2409.07790","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-tagging-with-large-language-model","title":"Knowledge Tagging with Large Language Model based Multi-Agent System","date":"2024-09-12","arxiv_id":"2409.08406","repositories_listed":0,"syntology":null},{"url":null,"slug":"omniquery-contextually-augmenting-captured","title":"OmniQuery: Contextually Augmenting Captured Multimodal Memory to Enable Personal Question Answering","date":"2024-09-12","arxiv_id":"2409.08250","repositories_listed":0,"syntology":null},{"url":null,"slug":"stable-language-model-pre-training-by","title":"Stable Language Model Pre-training by Reducing Embedding Variability","date":"2024-09-12","arxiv_id":"2409.07787","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-clc-uket-dataset-benchmarking-case","title":"The CLC-UKET Dataset: Benchmarking Case Outcome Prediction for the UK Employment Tribunal","date":"2024-09-12","arxiv_id":"2409.08098","repositories_listed":0,"syntology":null},{"url":null,"slug":"awaking-the-slides-a-tuning-free-and","title":"Awaking the Slides: A Tuning-free and Knowledge-regulated AI Tutoring System via Language Model Coordination","date":"2024-09-11","arxiv_id":"2409.07372","repositories_listed":0,"syntology":null},{"url":null,"slug":"explanation-debate-align-a-weak-to-strong","title":"Explanation, Debate, Align: A Weak-to-Strong Framework for Language Model Generalization","date":"2024-09-11","arxiv_id":"2409.07335","repositories_listed":0,"syntology":null},{"url":null,"slug":"freeride-harvesting-bubbles-in-pipeline","title":"FreeRide: Harvesting Bubbles in Pipeline Parallelism","date":"2024-09-11","arxiv_id":"2409.06941","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-unstructured-text-data-for","title":"Leveraging Unstructured Text Data for Federated Instruction Tuning of Large Language Models","date":"2024-09-11","arxiv_id":"2409.07136","repositories_listed":0,"syntology":null},{"url":null,"slug":"store-streamlining-semantic-tokenization-and","title":"STORE: Streamlining Semantic Tokenization and Generative Recommendation with A Single LLM","date":"2024-09-11","arxiv_id":"2409.07276","repositories_listed":0,"syntology":null},{"url":null,"slug":"when-less-is-not-more-large-language-models","title":"Mapping Biomedical Ontology Terms to IDs: Effect of Domain Prevalence on Prediction Accuracy","date":"2024-09-11","arxiv_id":"2409.13746","repositories_listed":0,"syntology":null},{"url":null,"slug":"accelerating-large-language-model-pretraining","title":"Accelerating Large Language Model Pretraining via LFR Pedagogy: Learn, Focus, and Review","date":"2024-09-10","arxiv_id":"2409.06131","repositories_listed":0,"syntology":null},{"url":null,"slug":"dipt-enhancing-llm-reasoning-through","title":"DiPT: Enhancing LLM reasoning through diversified perspective-taking","date":"2024-09-10","arxiv_id":"2409.06241","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-temporal-understanding-in-audio","title":"Enhancing Temporal Understanding in Audio Question Answering for Large Audio Language Models","date":"2024-09-10","arxiv_id":"2409.06223","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierllm-hierarchical-large-language-model-for","title":"HierLLM: Hierarchical Large Language Model for Question Recommendation","date":"2024-09-10","arxiv_id":"2409.06177","repositories_listed":0,"syntology":null},{"url":null,"slug":"intra-interaction-relationship-aware-weakly","title":"INTRA: Interaction Relationship-aware Weakly Supervised Affordance Grounding","date":"2024-09-10","arxiv_id":"2409.06210","repositories_listed":0,"syntology":null},{"url":null,"slug":"magda-multi-agent-guideline-driven-diagnostic","title":"MAGDA: Multi-agent guideline-driven diagnostic assistance","date":"2024-09-10","arxiv_id":"2409.06351","repositories_listed":0,"syntology":null},{"url":null,"slug":"mathglm-vision-solving-mathematical-problems","title":"MathGLM-Vision: Solving Mathematical Problems with Multi-Modal Large Language Model","date":"2024-09-10","arxiv_id":"2409.13729","repositories_listed":0,"syntology":null},{"url":null,"slug":"mip-gaf-a-mllm-annotated-benchmark-for-most","title":"MIP-GAF: A MLLM-annotated Benchmark for Most Important Person Localization and Group Context Understanding","date":"2024-09-10","arxiv_id":"2409.06224","repositories_listed":0,"syntology":null},{"url":null,"slug":"multimodal-large-language-model-driven","title":"Multimodal Large Language Model Driven Scenario Testing for Autonomous Vehicles","date":"2024-09-10","arxiv_id":"2409.06450","repositories_listed":0,"syntology":null},{"url":null,"slug":"topochat-enhancing-topological-materials","title":"Enhancing Large Language Models with Domain-Specific Knowledge: The Case in Topological Materials","date":"2024-09-10","arxiv_id":"2409.13732","repositories_listed":0,"syntology":null},{"url":null,"slug":"user-preferences-for-large-language-model","title":"User Preferences for Large Language Model versus Template-Based Explanations of Movie Recommendations: A Pilot Study","date":"2024-09-10","arxiv_id":"2409.06297","repositories_listed":0,"syntology":null}],"record_sha256":"9b83e20c56632901c2330643297e147ad48637dd2d5c51ef67cbbd9fee88d6e6","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}