{"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/90","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":90,"pages_in_order":177,"rows_per_page":100,"rows":[8901,9000],"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/89","next":"/task/language-modelling/papers/91","papers":[{"url":null,"slug":"sssd-simply-scalable-speculative-decoding","title":"SSSD: Simply-Scalable Speculative Decoding","date":"2024-11-08","arxiv_id":"2411.05894","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-empirical-impact-of-data-sanitization-on","title":"The Empirical Impact of Data Sanitization on Language Models","date":"2024-11-08","arxiv_id":"2411.05978","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-multi-modal-mastery-a-4-5b-parameter","title":"Towards Multi-Modal Mastery: A 4.5B Parameter Truly Multi-Modal Small Language Model","date":"2024-11-08","arxiv_id":"2411.05903","repositories_listed":0,"syntology":null},{"url":null,"slug":"unmasking-the-shadows-pinpoint-the","title":"Unmasking the Shadows: Pinpoint the Implementations of Anti-Dynamic Analysis Techniques in Malware Using LLM","date":"2024-11-08","arxiv_id":"2411.05982","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-reinforcement-learning-based-automatic","title":"A Reinforcement Learning-Based Automatic Video Editing Method Using Pre-trained Vision-Language Model","date":"2024-11-07","arxiv_id":"2411.04942","repositories_listed":0,"syntology":null},{"url":null,"slug":"benchmarking-large-language-models-with-1","title":"Benchmarking Large Language Models with Integer Sequence Generation Tasks","date":"2024-11-07","arxiv_id":"2411.04372","repositories_listed":0,"syntology":null},{"url":null,"slug":"cuify-the-xr-an-open-source-package-to-embed","title":"CUIfy the XR: An Open-Source Package to Embed LLM-powered Conversational Agents in XR","date":"2024-11-07","arxiv_id":"2411.04671","repositories_listed":0,"syntology":null},{"url":null,"slug":"scaling-laws-for-pre-training-agents-and","title":"Scaling Laws for Pre-training Agents and World Models","date":"2024-11-07","arxiv_id":"2411.04434","repositories_listed":0,"syntology":null},{"url":null,"slug":"videoglamm-a-large-multimodal-model-for-pixel","title":"VideoGLaMM: A Large Multimodal Model for Pixel-Level Visual Grounding in Videos","date":"2024-11-07","arxiv_id":"2411.04923","repositories_listed":0,"syntology":null},{"url":null,"slug":"vtechagp-an-academic-to-general-audience-text","title":"VTechAGP: An Academic-to-General-Audience Text Paraphrase Dataset and Benchmark Models","date":"2024-11-07","arxiv_id":"2411.04825","repositories_listed":0,"syntology":null},{"url":null,"slug":"watermarking-language-models-through-language","title":"Watermarking Language Models through Language Models","date":"2024-11-07","arxiv_id":"2411.05091","repositories_listed":0,"syntology":null},{"url":null,"slug":"deploying-multi-task-online-server-with-large","title":"Deploying Multi-task Online Server with Large Language Model","date":"2024-11-06","arxiv_id":"2411.03644","repositories_listed":0,"syntology":null},{"url":null,"slug":"fine-tuning-vision-language-model-for","title":"Fine-Tuning Vision-Language Model for Automated Engineering Drawing Information Extraction","date":"2024-11-06","arxiv_id":"2411.03707","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-generative-model-assisted-talking-face","title":"Large Generative Model-assisted Talking-face Semantic Communication System","date":"2024-11-06","arxiv_id":"2411.03876","repositories_listed":0,"syntology":null},{"url":null,"slug":"neurips-2023-competition-privacy-preserving","title":"NeurIPS 2023 Competition: Privacy Preserving Federated Learning Document VQA","date":"2024-11-06","arxiv_id":"2411.03730","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-n-grammys-accelerating-autoregressive","title":"The N-Grammys: Accelerating Autoregressive Inference with Learning-Free Batched Speculation","date":"2024-11-06","arxiv_id":"2411.03786","repositories_listed":0,"syntology":null},{"url":null,"slug":"ai-metropolis-scaling-large-language-model","title":"AI Metropolis: Scaling Large Language Model-based Multi-Agent Simulation with Out-of-order Execution","date":"2024-11-05","arxiv_id":"2411.03519","repositories_listed":0,"syntology":null},{"url":null,"slug":"chatgpt-in-research-and-education-exploring","title":"ChatGPT in Research and Education: Exploring Benefits and Threats","date":"2024-11-05","arxiv_id":"2411.02816","repositories_listed":0,"syntology":null},{"url":null,"slug":"controlling-for-unobserved-confounding-with","title":"Controlling for Unobserved Confounding with Large Language Model Classification of Patient Smoking Status","date":"2024-11-05","arxiv_id":"2411.03004","repositories_listed":0,"syntology":null},{"url":null,"slug":"humanvlm-foundation-for-human-scene-vision","title":"HumanVLM: Foundation for Human-Scene Vision-Language Model","date":"2024-11-05","arxiv_id":"2411.03034","repositories_listed":0,"syntology":null},{"url":null,"slug":"persianrag-a-retrieval-augmented-generation","title":"PersianRAG: A Retrieval-Augmented Generation System for Persian Language","date":"2024-11-05","arxiv_id":"2411.02832","repositories_listed":0,"syntology":null},{"url":null,"slug":"predictor-corrector-enhanced-transformers","title":"Predictor-Corrector Enhanced Transformers with Exponential Moving Average Coefficient Learning","date":"2024-11-05","arxiv_id":"2411.03042","repositories_listed":0,"syntology":null},{"url":null,"slug":"spontaneous-emergence-of-agent-individuality","title":"Spontaneous Emergence of Agent Individuality through Social Interactions in LLM-Based Communities","date":"2024-11-05","arxiv_id":"2411.03252","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-evolution-of-rwkv-advancements-in","title":"The Evolution of RWKV: Advancements in Efficient Language Modeling","date":"2024-11-05","arxiv_id":"2411.02795","repositories_listed":0,"syntology":null},{"url":null,"slug":"unified-pathological-speech-analysis-with","title":"Unified Pathological Speech Analysis with Prompt Tuning","date":"2024-11-05","arxiv_id":"2411.04142","repositories_listed":0,"syntology":null},{"url":null,"slug":"vision-paper-probot-enhancing-patient","title":"[Vision Paper] PRObot: Enhancing Patient-Reported Outcome Measures for Diabetic Retinopathy using Chatbots and Generative AI","date":"2024-11-05","arxiv_id":"2411.02973","repositories_listed":0,"syntology":null},{"url":null,"slug":"avss-layer-importance-evaluation-in-large","title":"AVSS: Layer Importance Evaluation in Large Language Models via Activation Variance-Sparsity Analysis","date":"2024-11-04","arxiv_id":"2411.02117","repositories_listed":0,"syntology":null},{"url":null,"slug":"chattracker-enhancing-visual-tracking","title":"ChatTracker: Enhancing Visual Tracking Performance via Chatting with Multimodal Large Language Model","date":"2024-11-04","arxiv_id":"2411.01756","repositories_listed":0,"syntology":null},{"url":null,"slug":"context-parallelism-for-scalable-million","title":"Context Parallelism for Scalable Million-Token Inference","date":"2024-11-04","arxiv_id":"2411.01783","repositories_listed":0,"syntology":null},{"url":null,"slug":"graphvl-graph-enhanced-semantic-modeling-via","title":"GraphVL: Graph-Enhanced Semantic Modeling via Vision-Language Models for Generalized Class Discovery","date":"2024-11-04","arxiv_id":"2411.02074","repositories_listed":0,"syntology":null},{"url":null,"slug":"kptllm-unveiling-the-power-of-large-language","title":"KptLLM: Unveiling the Power of Large Language Model for Keypoint Comprehension","date":"2024-11-04","arxiv_id":"2411.01846","repositories_listed":0,"syntology":null},{"url":null,"slug":"wave-network-an-ultra-small-language-model","title":"Wave Network: An Ultra-Small Language Model","date":"2024-11-04","arxiv_id":"2411.02674","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-deep-dive-into-large-language-model-code","title":"A Deep Dive Into Large Language Model Code Generation Mistakes: What and Why?","date":"2024-11-03","arxiv_id":"2411.01414","repositories_listed":0,"syntology":null},{"url":null,"slug":"enriching-tabular-data-with-contextual-llm","title":"Enriching Tabular Data with Contextual LLM Embeddings: A Comprehensive Ablation Study for Ensemble Classifiers","date":"2024-11-03","arxiv_id":"2411.01645","repositories_listed":0,"syntology":null},{"url":null,"slug":"high-performance-automated-abstract-screening","title":"High-performance automated abstract screening with large language model ensembles","date":"2024-11-03","arxiv_id":"2411.02451","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-model-supply-chain-open","title":"Large Language Model Supply Chain: Open Problems From the Security Perspective","date":"2024-11-03","arxiv_id":"2411.01604","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-mechanistic-explanatory-strategy-for-xai","title":"A Mechanistic Explanatory Strategy for XAI","date":"2024-11-02","arxiv_id":"2411.01332","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-humans-oversee-agents-to-prevent-privacy","title":"Privacy Leakage Overshadowed by Views of AI: A Study on Human Oversight of Privacy in Language Model Agent","date":"2024-11-02","arxiv_id":"2411.01344","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-large-language-model-predict-employee","title":"Can Large Language Model Predict Employee Attrition?","date":"2024-11-02","arxiv_id":"2411.01353","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-multimodal-large-language-model-think","title":"Can Multimodal Large Language Model Think Analogically?","date":"2024-11-02","arxiv_id":"2411.01307","repositories_listed":0,"syntology":null},{"url":null,"slug":"interacting-large-language-model-agents","title":"Interacting Large Language Model Agents. Interpretable Models and Social Learning","date":"2024-11-02","arxiv_id":"2411.01271","repositories_listed":0,"syntology":null},{"url":null,"slug":"primo-progressive-induction-for-multi-hop","title":"PRIMO: Progressive Induction for Multi-hop Open Rule Generation","date":"2024-11-02","arxiv_id":"2411.01205","repositories_listed":0,"syntology":null},{"url":null,"slug":"swan-and-arabicmteb-dialect-aware-arabic","title":"Swan and ArabicMTEB: Dialect-Aware, Arabic-Centric, Cross-Lingual, and Cross-Cultural Embedding Models and Benchmarks","date":"2024-11-02","arxiv_id":"2411.01192","repositories_listed":0,"syntology":null},{"url":null,"slug":"adding-error-bars-to-evals-a-statistical","title":"Adding Error Bars to Evals: A Statistical Approach to Language Model Evaluations","date":"2024-11-01","arxiv_id":"2411.00640","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-aac-software-for-dysarthric","title":"Enhancing AAC Software for Dysarthric Speakers in e-Health Settings: An Evaluation Using TORGO","date":"2024-11-01","arxiv_id":"2411.00980","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-the-traditional-chinese-medicine","title":"Enhancing the Traditional Chinese Medicine Capabilities of Large Language Model through Reinforcement Learning from AI Feedback","date":"2024-11-01","arxiv_id":"2411.00897","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-few-shot-cross-domain-named-entity","title":"Improving Few-Shot Cross-Domain Named Entity Recognition by Instruction Tuning a Word-Embedding based Retrieval Augmented Large Language Model","date":"2024-11-01","arxiv_id":"2411.00451","repositories_listed":0,"syntology":null},{"url":null,"slug":"llm-kt-a-versatile-framework-for-knowledge","title":"LLM-KT: A Versatile Framework for Knowledge Transfer from Large Language Models to Collaborative Filtering","date":"2024-11-01","arxiv_id":"2411.00556","repositories_listed":0,"syntology":null},{"url":null,"slug":"radflag-a-black-box-hallucination-detection","title":"RadFlag: A Black-Box Hallucination Detection Method for Medical Vision Language Models","date":"2024-11-01","arxiv_id":"2411.00299","repositories_listed":0,"syntology":null},{"url":null,"slug":"respact-harmonizing-reasoning-speaking-and","title":"ReSpAct: Harmonizing Reasoning, Speaking, and Acting Towards Building Large Language Model-Based Conversational AI Agents","date":"2024-11-01","arxiv_id":"2411.00927","repositories_listed":0,"syntology":null},{"url":"/paper/spring-lab-iitm-s-submission-to-low-resource","slug":"spring-lab-iitm-s-submission-to-low-resource","title":"SPRING Lab IITM's submission to Low Resource Indic Language Translation Shared Task","date":"2024-11-01","arxiv_id":"2411.00727","repositories_listed":0,"syntology":null},{"url":null,"slug":"unified-generative-and-discriminative","title":"Unified Generative and Discriminative Training for Multi-modal Large Language Models","date":"2024-11-01","arxiv_id":"2411.00304","repositories_listed":0,"syntology":null},{"url":null,"slug":"alise-accelerating-large-language-model","title":"ALISE: Accelerating Large Language Model Serving with Speculative Scheduling","date":"2024-10-31","arxiv_id":"2410.23537","repositories_listed":0,"syntology":null},{"url":null,"slug":"beyond-label-attention-transparency-in","title":"Beyond Label Attention: Transparency in Language Models for Automated Medical Coding via Dictionary Learning","date":"2024-10-31","arxiv_id":"2411.00173","repositories_listed":0,"syntology":null},{"url":null,"slug":"derec-simpro-unlock-language-model-benefits","title":"DEREC-SIMPRO: unlock Language Model benefits to advance Synthesis in Data Clean Room","date":"2024-10-31","arxiv_id":"2411.00879","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-context-to-action-analysis-of-the-impact","title":"From Context to Action: Analysis of the Impact of State Representation and Context on the Generalization of Multi-Turn Web Navigation Agents","date":"2024-10-31","arxiv_id":"2410.23555","repositories_listed":0,"syntology":null},{"url":"/paper/matchmaker-self-improving-large-language","slug":"matchmaker-self-improving-large-language","title":"Matchmaker: Self-Improving Large Language Model Programs for Schema Matching","date":"2024-10-31","arxiv_id":"2410.24105","repositories_listed":0,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/matchmaker-self-improving-large-language#ran","syntology_url":"https://syntology.ai/paper/2410.24105","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.24105"}},"official":null}},{"url":null,"slug":"mess-energy-optimal-inferencing-in-language","title":"MESS+: Energy-Optimal Inferencing in Language Model Zoos with Service Level Guarantees","date":"2024-10-31","arxiv_id":"2411.00889","repositories_listed":0,"syntology":null},{"url":null,"slug":"morphological-typology-in-bpe-subword","title":"Morphological Typology in BPE Subword Productivity and Language Modeling","date":"2024-10-31","arxiv_id":"2410.23656","repositories_listed":0,"syntology":null},{"url":null,"slug":"p-0-a-vision-language-action-flow-model-for","title":"$π_0$: A Vision-Language-Action Flow Model for General Robot Control","date":"2024-10-31","arxiv_id":"2410.24164","repositories_listed":0,"syntology":null},{"url":null,"slug":"representative-social-choice-from-learning","title":"Representative Social Choice: From Learning Theory to AI Alignment","date":"2024-10-31","arxiv_id":"2410.23953","repositories_listed":0,"syntology":null},{"url":null,"slug":"schema-augmentation-for-zero-shot-domain","title":"Schema Augmentation for Zero-Shot Domain Adaptation in Dialogue State Tracking","date":"2024-10-31","arxiv_id":"2411.00150","repositories_listed":0,"syntology":null},{"url":null,"slug":"stereo-talker-audio-driven-3d-human-synthesis","title":"Stereo-Talker: Audio-driven 3D Human Synthesis with Prior-Guided Mixture-of-Experts","date":"2024-10-31","arxiv_id":"2410.23836","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-npu-hwc-system-for-the-iscslp-2024","title":"The NPU-HWC System for the ISCSLP 2024 Inspirational and Convincing Audio Generation Challenge","date":"2024-10-31","arxiv_id":"2410.23815","repositories_listed":0,"syntology":null},{"url":null,"slug":"thought-space-explorer-navigating-and","title":"Thought Space Explorer: Navigating and Expanding Thought Space for Large Language Model Reasoning","date":"2024-10-31","arxiv_id":"2410.24155","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-reliable-alignment-uncertainty-aware","title":"Towards Reliable Alignment: Uncertainty-aware RLHF","date":"2024-10-31","arxiv_id":"2410.23726","repositories_listed":0,"syntology":null},{"url":null,"slug":"web-scale-visual-entity-recognition-an-llm","title":"Web-Scale Visual Entity Recognition: An LLM-Driven Data Approach","date":"2024-10-31","arxiv_id":"2410.23676","repositories_listed":0,"syntology":null},{"url":null,"slug":"weight-decay-induces-low-rank-attention","title":"Weight decay induces low-rank attention layers","date":"2024-10-31","arxiv_id":"2410.23819","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-monte-carlo-framework-for-calibrated","title":"A Monte Carlo Framework for Calibrated Uncertainty Estimation in Sequence Prediction","date":"2024-10-30","arxiv_id":"2410.23272","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-theoretical-perspective-for-speculative","title":"A Theoretical Perspective for Speculative Decoding Algorithm","date":"2024-10-30","arxiv_id":"2411.00841","repositories_listed":0,"syntology":null},{"url":null,"slug":"all-or-none-identifiable-linear-properties-of","title":"All or None: Identifiable Linear Properties of Next-token Predictors in Language Modeling","date":"2024-10-30","arxiv_id":"2410.23501","repositories_listed":0,"syntology":null},{"url":null,"slug":"constructing-multimodal-datasets-from-scratch","title":"Constructing Multimodal Datasets from Scratch for Rapid Development of a Japanese Visual Language Model","date":"2024-10-30","arxiv_id":"2410.22736","repositories_listed":0,"syntology":null},{"url":null,"slug":"dynamic-information-sub-selection-for","title":"Dynamic Information Sub-Selection for Decision Support","date":"2024-10-30","arxiv_id":"2410.23423","repositories_listed":0,"syntology":null},{"url":null,"slug":"explainable-behavior-cloning-teaching-large","title":"Explainable Behavior Cloning: Teaching Large Language Model Agents through Learning by Demonstration","date":"2024-10-30","arxiv_id":"2410.22916","repositories_listed":0,"syntology":null},{"url":null,"slug":"ip-mot-instance-prompt-learning-for-cross","title":"IP-MOT: Instance Prompt Learning for Cross-Domain Multi-Object Tracking","date":"2024-10-30","arxiv_id":"2410.23907","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-and-transferring-sparse-contextual","title":"Learning and Transferring Sparse Contextual Bigrams with Linear Transformers","date":"2024-10-30","arxiv_id":"2410.23438","repositories_listed":0,"syntology":null},{"url":null,"slug":"prove-your-point-bringing-proof-enhancement","title":"Prove Your Point!: Bringing Proof-Enhancement Principles to Argumentative Essay Generation","date":"2024-10-30","arxiv_id":"2410.22642","repositories_listed":0,"syntology":null},{"url":"/paper/pv-vtt-a-privacy-centric-dataset-for-mission","slug":"pv-vtt-a-privacy-centric-dataset-for-mission","title":"PV-VTT: A Privacy-Centric Dataset for Mission-Specific Anomaly Detection and Natural Language Interpretation","date":"2024-10-30","arxiv_id":"2410.22623","repositories_listed":0,"syntology":null},{"url":null,"slug":"robotic-state-recognition-with-image-to-text","title":"Robotic State Recognition with Image-to-Text Retrieval Task of Pre-Trained Vision-Language Model and Black-Box Optimization","date":"2024-10-30","arxiv_id":"2410.22707","repositories_listed":0,"syntology":null},{"url":null,"slug":"smaller-large-language-models-can-do-moral","title":"Smaller Large Language Models Can Do Moral Self-Correction","date":"2024-10-30","arxiv_id":"2410.23496","repositories_listed":0,"syntology":null},{"url":null,"slug":"teaching-a-language-model-to-distinguish","title":"Teaching a Language Model to Distinguish Between Similar Details using a Small Adversarial Training Set","date":"2024-10-30","arxiv_id":"2410.23118","repositories_listed":0,"syntology":null},{"url":"/paper/toward-understanding-in-context-vs-in-weight","slug":"toward-understanding-in-context-vs-in-weight","title":"Toward Understanding In-context vs. In-weight Learning","date":"2024-10-30","arxiv_id":"2410.23042","repositories_listed":0,"syntology":{"n":12,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":7,"n_pointer_only":12,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/toward-understanding-in-context-vs-in-weight#ran","syntology_url":"https://syntology.ai/paper/2410.23042","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.23042"}},"official":null}},{"url":null,"slug":"visualpredicator-learning-abstract-world","title":"VisualPredicator: Learning Abstract World Models with Neuro-Symbolic Predicates for Robot Planning","date":"2024-10-30","arxiv_id":"2410.23156","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-hierarchical-language-model-for","title":"A Hierarchical Language Model For Interpretable Graph Reasoning","date":"2024-10-29","arxiv_id":"2410.22372","repositories_listed":0,"syntology":null},{"url":"/paper/abrupt-learning-in-transformers-a-case-study","slug":"abrupt-learning-in-transformers-a-case-study","title":"Abrupt Learning in Transformers: A Case Study on Matrix Completion","date":"2024-10-29","arxiv_id":"2410.22244","repositories_listed":0,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/abrupt-learning-in-transformers-a-case-study#ran","syntology_url":"https://syntology.ai/paper/2410.22244","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.22244"}},"official":null}},{"url":null,"slug":"anticipating-future-with-large-language-model","title":"Anticipating Future with Large Language Model for Simultaneous Machine Translation","date":"2024-10-29","arxiv_id":"2410.22499","repositories_listed":0,"syntology":null},{"url":null,"slug":"auto-intent-automated-intent-discovery-and","title":"Auto-Intent: Automated Intent Discovery and Self-Exploration for Large Language Model Web Agents","date":"2024-10-29","arxiv_id":"2410.22552","repositories_listed":0,"syntology":null},{"url":null,"slug":"curategpt-a-flexible-language-model-assisted","title":"CurateGPT: A flexible language-model assisted biocuration tool","date":"2024-10-29","arxiv_id":"2411.00046","repositories_listed":0,"syntology":null},{"url":null,"slug":"democratizing-reward-design-for-personal-and","title":"Democratizing Reward Design for Personal and Representative Value-Alignment","date":"2024-10-29","arxiv_id":"2410.22203","repositories_listed":0,"syntology":null},{"url":null,"slug":"discrete-modeling-via-boundary-conditional","title":"Discrete Modeling via Boundary Conditional Diffusion Processes","date":"2024-10-29","arxiv_id":"2410.22380","repositories_listed":0,"syntology":null},{"url":null,"slug":"factbench-a-dynamic-benchmark-for-in-the-wild","title":"FactBench: A Dynamic Benchmark for In-the-Wild Language Model Factuality Evaluation","date":"2024-10-29","arxiv_id":"2410.22257","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-melodic-note-sequences-to-pitches-using","title":"From melodic note sequences to pitches using word2vec","date":"2024-10-29","arxiv_id":"2410.22285","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-and-unlearning-of-fabricated","title":"Learning and Unlearning of Fabricated Knowledge in Language Models","date":"2024-10-29","arxiv_id":"2410.21750","repositories_listed":0,"syntology":null},{"url":null,"slug":"marco-multi-agent-real-time-chat","title":"MARCO: Multi-Agent Real-time Chat Orchestration","date":"2024-10-29","arxiv_id":"2410.21784","repositories_listed":0,"syntology":null},{"url":null,"slug":"motiongpt-2-a-general-purpose-motion-language","title":"MotionGPT-2: A General-Purpose Motion-Language Model for Motion Generation and Understanding","date":"2024-10-29","arxiv_id":"2410.21747","repositories_listed":0,"syntology":null},{"url":null,"slug":"reliable-semantic-understanding-for-real","title":"Reliable Semantic Understanding for Real World Zero-shot Object Goal Navigation","date":"2024-10-29","arxiv_id":"2410.21926","repositories_listed":0,"syntology":null},{"url":null,"slug":"vl-cache-sparsity-and-modality-aware-kv-cache","title":"VL-Cache: Sparsity and Modality-Aware KV Cache Compression for Vision-Language Model Inference Acceleration","date":"2024-10-29","arxiv_id":"2410.23317","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-actor-critic-approach-to-boosting-text-to","title":"An Actor-Critic Approach to Boosting Text-to-SQL Large Language Model","date":"2024-10-28","arxiv_id":"2410.22082","repositories_listed":0,"syntology":null},{"url":null,"slug":"bongllama-llama-for-bangla-language","title":"BongLLaMA: LLaMA for Bangla Language","date":"2024-10-28","arxiv_id":"2410.21200","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-machines-think-like-humans-a-behavioral","title":"Can Machines Think Like Humans? A Behavioral Evaluation of LLM-Agents in Dictator Games","date":"2024-10-28","arxiv_id":"2410.21359","repositories_listed":0,"syntology":null}],"record_sha256":"58416b50773230be9bc65968f55fef442502cc1425ebf1f319985d54db55c8ce","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}