{"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/99","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":99,"pages_in_order":177,"rows_per_page":100,"rows":[9801,9900],"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/98","next":"/task/language-modelling/papers/100","papers":[{"url":null,"slug":"meltemi-the-first-open-large-language-model","title":"Meltemi: The first open Large Language Model for Greek","date":"2024-07-30","arxiv_id":"2407.20743","repositories_listed":0,"syntology":null},{"url":null,"slug":"mimicking-the-mavens-agent-based-opinion","title":"Mimicking the Mavens: Agent-based Opinion Synthesis and Emotion Prediction for Social Media Influencers","date":"2024-07-30","arxiv_id":"2407.20668","repositories_listed":0,"syntology":null},{"url":null,"slug":"2407-21075","title":"Apple Intelligence Foundation Language Models","date":"2024-07-29","arxiv_id":"2407.21075","repositories_listed":0,"syntology":null},{"url":null,"slug":"beyond-metrics-a-critical-analysis-of-the","title":"Beyond Metrics: A Critical Analysis of the Variability in Large Language Model Evaluation Frameworks","date":"2024-07-29","arxiv_id":"2407.21072","repositories_listed":0,"syntology":null},{"url":null,"slug":"gender-race-and-intersectional-bias-in-resume","title":"Gender, Race, and Intersectional Bias in Resume Screening via Language Model Retrieval","date":"2024-07-29","arxiv_id":"2407.20371","repositories_listed":0,"syntology":null},{"url":null,"slug":"harnessing-large-vision-and-language-models","title":"Harnessing Large Vision and Language Models in Agriculture: A Review","date":"2024-07-29","arxiv_id":"2407.19679","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-retrieval-augmented-language-model","title":"Improving Retrieval Augmented Language Model with Self-Reasoning","date":"2024-07-29","arxiv_id":"2407.19813","repositories_listed":0,"syntology":null},{"url":null,"slug":"ml-mamba-efficient-multi-modal-large-language","title":"ML-Mamba: Efficient Multi-Modal Large Language Model Utilizing Mamba-2","date":"2024-07-29","arxiv_id":"2407.19832","repositories_listed":0,"syntology":null},{"url":null,"slug":"normality-addition-via-normality-detection-in","title":"Normality Addition via Normality Detection in Industrial Image Anomaly Detection Models","date":"2024-07-29","arxiv_id":"2407.19849","repositories_listed":0,"syntology":null},{"url":null,"slug":"specify-and-edit-overcoming-ambiguity-in-text","title":"Specify and Edit: Overcoming Ambiguity in Text-Based Image Editing","date":"2024-07-29","arxiv_id":"2407.20232","repositories_listed":0,"syntology":null},{"url":null,"slug":"voldoger-llm-assisted-datasets-for-domain","title":"VolDoGer: LLM-assisted Datasets for Domain Generalization in Vision-Language Tasks","date":"2024-07-29","arxiv_id":"2407.19795","repositories_listed":0,"syntology":null},{"url":null,"slug":"2407-21065","title":"LawLLM: Law Large Language Model for the US Legal System","date":"2024-07-27","arxiv_id":"2407.21065","repositories_listed":0,"syntology":null},{"url":null,"slug":"farssibert-a-novel-transformer-based-model","title":"FarSSiBERT: A Novel Transformer-based Model for Semantic Similarity Measurement of Persian Social Networks Informal Texts","date":"2024-07-27","arxiv_id":"2407.19173","repositories_listed":0,"syntology":null},{"url":null,"slug":"gp-vls-a-general-purpose-vision-language","title":"GP-VLS: A general-purpose vision language model for surgery","date":"2024-07-27","arxiv_id":"2407.19305","repositories_listed":0,"syntology":null},{"url":null,"slug":"llava-read-enhancing-reading-ability-of","title":"LLaVA-Read: Enhancing Reading Ability of Multimodal Language Models","date":"2024-07-27","arxiv_id":"2407.19185","repositories_listed":0,"syntology":null},{"url":null,"slug":"2408-00804","title":"ChipExpert: The Open-Source Integrated-Circuit-Design-Specific Large Language Model","date":"2024-07-26","arxiv_id":"2408.00804","repositories_listed":0,"syntology":null},{"url":null,"slug":"blockchain-for-large-language-model-security","title":"Blockchain for Large Language Model Security and Safety: A Holistic Survey","date":"2024-07-26","arxiv_id":"2407.20181","repositories_listed":0,"syntology":null},{"url":null,"slug":"effective-large-language-model-debugging-with","title":"Effective Large Language Model Debugging with Best-first Tree Search","date":"2024-07-26","arxiv_id":"2407.19055","repositories_listed":0,"syntology":null},{"url":null,"slug":"graph-based-unsupervised-disentangled","title":"Graph-based Unsupervised Disentangled Representation Learning via Multimodal Large Language Models","date":"2024-07-26","arxiv_id":"2407.18999","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-model-agent-in-financial","title":"Large Language Model Agent in Financial Trading: A Survey","date":"2024-07-26","arxiv_id":"2408.06361","repositories_listed":0,"syntology":null},{"url":null,"slug":"mistralbsm-leveraging-mistral-7b-for","title":"MistralBSM: Leveraging Mistral-7B for Vehicular Networks Misbehavior Detection","date":"2024-07-26","arxiv_id":"2407.18462","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-turn-response-selection-with","title":"Multi-turn Response Selection with Commonsense-enhanced Language Models","date":"2024-07-26","arxiv_id":"2407.18479","repositories_listed":0,"syntology":null},{"url":null,"slug":"reaper-reasoning-based-retrieval-planning-for","title":"REAPER: Reasoning based Retrieval Planning for Complex RAG Systems","date":"2024-07-26","arxiv_id":"2407.18553","repositories_listed":0,"syntology":null},{"url":null,"slug":"dallah-a-dialect-aware-multimodal-large","title":"Dallah: A Dialect-Aware Multimodal Large Language Model for Arabic","date":"2024-07-25","arxiv_id":"2407.18129","repositories_listed":0,"syntology":null},{"url":null,"slug":"describe-where-you-are-improving-noise","title":"Describe Where You Are: Improving Noise-Robustness for Speech Emotion Recognition with Text Description of the Environment","date":"2024-07-25","arxiv_id":"2407.17716","repositories_listed":0,"syntology":null},{"url":null,"slug":"examining-the-influence-of-political-bias-on","title":"Examining the Influence of Political Bias on Large Language Model Performance in Stance Classification","date":"2024-07-25","arxiv_id":"2407.17688","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-domain-specific-asr-with-llm","title":"Improving Domain-Specific ASR with LLM-Generated Contextual Descriptions","date":"2024-07-25","arxiv_id":"2407.17874","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-model-integrated-healthcare","title":"Large Language Model Integrated Healthcare Cyber-Physical Systems Architecture","date":"2024-07-25","arxiv_id":"2407.18407","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-group-uncertainty-quantification-for","title":"Multi-group Uncertainty Quantification for Long-form Text Generation","date":"2024-07-25","arxiv_id":"2407.21057","repositories_listed":0,"syntology":null},{"url":null,"slug":"recursive-introspection-teaching-language","title":"Recursive Introspection: Teaching Language Model Agents How to Self-Improve","date":"2024-07-25","arxiv_id":"2407.18219","repositories_listed":0,"syntology":null},{"url":null,"slug":"twips-a-large-language-model-powered-texting","title":"TwIPS: A Large Language Model Powered Texting Application to Simplify Conversational Nuances for Autistic Users","date":"2024-07-25","arxiv_id":"2407.17760","repositories_listed":0,"syntology":null},{"url":null,"slug":"understanding-the-interplay-of-scale-data-and","title":"Understanding the Interplay of Scale, Data, and Bias in Language Models: A Case Study with BERT","date":"2024-07-25","arxiv_id":"2407.21058","repositories_listed":0,"syntology":null},{"url":null,"slug":"2408-01452","title":"Building a Domain-specific Guardrail Model in Production","date":"2024-07-24","arxiv_id":"2408.01452","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comprehensive-approach-to-misspelling","title":"A Comprehensive Approach to Misspelling Correction with BERT and Levenshtein Distance","date":"2024-07-24","arxiv_id":"2407.17383","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-novel-two-step-fine-tuning-pipeline-for","title":"A Novel Two-Step Fine-Tuning Pipeline for Cold-Start Active Learning in Text Classification Tasks","date":"2024-07-24","arxiv_id":"2407.17284","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-voter-based-stochastic-rejection-method","title":"A Voter-Based Stochastic Rejection-Method Framework for Asymptotically Safe Language Model Outputs","date":"2024-07-24","arxiv_id":"2407.16994","repositories_listed":0,"syntology":null},{"url":null,"slug":"cheems-wonderful-matrices-more-efficient-and","title":"Wonderful Matrices: More Efficient and Effective Architecture for Language Modeling Tasks","date":"2024-07-24","arxiv_id":"2407.16958","repositories_listed":0,"syntology":null},{"url":null,"slug":"early-screening-of-potential-breakthrough","title":"Early screening of potential breakthrough technologies with enhanced interpretability: A patent-specific hierarchical attention network model","date":"2024-07-24","arxiv_id":"2407.16939","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-domain-robust-lightweight-reward","title":"Exploring Domain Robust Lightweight Reward Models based on Router Mechanism","date":"2024-07-24","arxiv_id":"2407.17546","repositories_listed":0,"syntology":null},{"url":null,"slug":"gradient-based-inference-of-abstract-task","title":"Gradient-based inference of abstract task representations for generalization in neural networks","date":"2024-07-24","arxiv_id":"2407.17356","repositories_listed":0,"syntology":null},{"url":null,"slug":"label-alignment-and-reassignment-with","title":"Label Alignment and Reassignment with Generalist Large Language Model for Enhanced Cross-Domain Named Entity Recognition","date":"2024-07-24","arxiv_id":"2407.17344","repositories_listed":0,"syntology":null},{"url":null,"slug":"sdoh-gpt-using-large-language-models-to","title":"SDoH-GPT: Using Large Language Models to Extract Social Determinants of Health (SDoH)","date":"2024-07-24","arxiv_id":"2407.17126","repositories_listed":0,"syntology":null},{"url":null,"slug":"simct-a-simple-consistency-test-protocol-in","title":"SimCT: A Simple Consistency Test Protocol in LLMs Development Lifecycle","date":"2024-07-24","arxiv_id":"2407.17150","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-transfer-unlearning-empirical","title":"Towards Transfer Unlearning: Empirical Evidence of Cross-Domain Bias Mitigation","date":"2024-07-24","arxiv_id":"2407.16951","repositories_listed":0,"syntology":null},{"url":null,"slug":"viper-visual-personalization-of-generative","title":"ViPer: Visual Personalization of Generative Models via Individual Preference Learning","date":"2024-07-24","arxiv_id":"2407.17365","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comparative-study-on-patient-language","title":"A Comparative Study on Patient Language across Therapeutic Domains for Effective Patient Voice Classification in Online Health Discussions","date":"2024-07-23","arxiv_id":"2407.16593","repositories_listed":0,"syntology":null},{"url":null,"slug":"do-llms-know-when-to-not-answer-investigating","title":"Do LLMs Know When to NOT Answer? Investigating Abstention Abilities of Large Language Models","date":"2024-07-23","arxiv_id":"2407.16221","repositories_listed":0,"syntology":null},{"url":null,"slug":"facttrack-time-aware-world-state-tracking-in","title":"FACTTRACK: Time-Aware World State Tracking in Story Outlines","date":"2024-07-23","arxiv_id":"2407.16347","repositories_listed":0,"syntology":null},{"url":null,"slug":"graph-structured-speculative-decoding","title":"Graph-Structured Speculative Decoding","date":"2024-07-23","arxiv_id":"2407.16207","repositories_listed":0,"syntology":null},{"url":"/paper/lawma-the-power-of-specialization-for-legal","slug":"lawma-the-power-of-specialization-for-legal","title":"Lawma: The Power of Specialization for Legal Tasks","date":"2024-07-23","arxiv_id":"2407.16615","repositories_listed":0,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/lawma-the-power-of-specialization-for-legal#ran","syntology_url":"https://syntology.ai/paper/2407.16615","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.16615"}},"official":null}},{"url":null,"slug":"networks-of-networks-complexity-class","title":"Networks of Networks: Complexity Class Principles Applied to Compound AI Systems Design","date":"2024-07-23","arxiv_id":"2407.16831","repositories_listed":0,"syntology":null},{"url":null,"slug":"occlusion-aware-3d-motion-interpretation-for","title":"Occlusion-Aware 3D Motion Interpretation for Abnormal Behavior Detection","date":"2024-07-23","arxiv_id":"2407.16788","repositories_listed":0,"syntology":null},{"url":null,"slug":"quantifying-the-role-of-textual","title":"Quantifying the Role of Textual Predictability in Automatic Speech Recognition","date":"2024-07-23","arxiv_id":"2407.16537","repositories_listed":0,"syntology":null},{"url":null,"slug":"allam-large-language-models-for-arabic-and","title":"ALLaM: Large Language Models for Arabic and English","date":"2024-07-22","arxiv_id":"2407.15390","repositories_listed":0,"syntology":null},{"url":null,"slug":"decoding-bacnet-packets-a-large-language","title":"Decoding BACnet Packets: A Large Language Model Approach for Packet Interpretation","date":"2024-07-22","arxiv_id":"2407.15428","repositories_listed":0,"syntology":null},{"url":null,"slug":"j-chat-japanese-large-scale-spoken-dialogue","title":"J-CHAT: Japanese Large-scale Spoken Dialogue Corpus for Spoken Dialogue Language Modeling","date":"2024-07-22","arxiv_id":"2407.15828","repositories_listed":0,"syntology":null},{"url":null,"slug":"llmexplainer-large-language-model-based","title":"LLMExplainer: Large Language Model based Bayesian Inference for Graph Explanation Generation","date":"2024-07-22","arxiv_id":"2407.15351","repositories_listed":0,"syntology":null},{"url":null,"slug":"omos-qa-a-dataset-for-cross-lingual","title":"OMoS-QA: A Dataset for Cross-Lingual Extractive Question Answering in a German Migration Context","date":"2024-07-22","arxiv_id":"2407.15736","repositories_listed":0,"syntology":null},{"url":null,"slug":"pre-training-and-prompting-for-few-shot-node","title":"Pre-Training and Prompting for Few-Shot Node Classification on Text-Attributed Graphs","date":"2024-07-22","arxiv_id":"2407.15431","repositories_listed":0,"syntology":null},{"url":null,"slug":"sam2clip2sam-vision-language-model-for","title":"SAM2CLIP2SAM: Vision Language Model for Segmentation of 3D CT Scans for Covid-19 Detection","date":"2024-07-22","arxiv_id":"2407.15728","repositories_listed":0,"syntology":null},{"url":null,"slug":"socialquotes-learning-contextual-roles-of","title":"SocialQuotes: Learning Contextual Roles of Social Media Quotes on the Web","date":"2024-07-22","arxiv_id":"2407.16007","repositories_listed":0,"syntology":null},{"url":null,"slug":"text-to-battery-recipe-a-language-modeling","title":"Text-to-Battery Recipe: A language modeling-based protocol for automatic battery recipe extraction and retrieval","date":"2024-07-22","arxiv_id":"2407.15459","repositories_listed":0,"syntology":null},{"url":null,"slug":"evidence-based-temporal-fact-verification","title":"Evidence-Based Temporal Fact Verification","date":"2024-07-21","arxiv_id":"2407.15291","repositories_listed":0,"syntology":null},{"url":"/paper/farewell-to-length-extrapolation-a-training","slug":"farewell-to-length-extrapolation-a-training","title":"ReAttention: Training-Free Infinite Context with Finite Attention Scope","date":"2024-07-21","arxiv_id":"2407.15176","repositories_listed":0,"syntology":{"n":7,"n_ran":5,"n_constructed":4,"n_ran_checked":4,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"5 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/farewell-to-length-extrapolation-a-training#ran","syntology_url":"https://syntology.ai/paper/2407.15176","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.15176"}},"official":null}},{"url":null,"slug":"learning-to-compile-programs-to-neural","title":"Learning to Compile Programs to Neural Networks","date":"2024-07-21","arxiv_id":"2407.15078","repositories_listed":0,"syntology":null},{"url":null,"slug":"relational-database-augmented-large-language","title":"Relational Database Augmented Large Language Model","date":"2024-07-21","arxiv_id":"2407.15071","repositories_listed":0,"syntology":null},{"url":null,"slug":"when-do-universal-image-jailbreaks-transfer","title":"Failures to Find Transferable Image Jailbreaks Between Vision-Language Models","date":"2024-07-21","arxiv_id":"2407.15211","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-vlms-be-used-on-videos-for-action","title":"Can VLMs be used on videos for action recognition? LLMs are Visual Reasoning Coordinators","date":"2024-07-20","arxiv_id":"2407.14834","repositories_listed":0,"syntology":null},{"url":null,"slug":"falcon2-11b-technical-report","title":"Falcon2-11B Technical Report","date":"2024-07-20","arxiv_id":"2407.14885","repositories_listed":0,"syntology":null},{"url":"/paper/generalization-v-s-memorization-tracing","slug":"generalization-v-s-memorization-tracing","title":"Generalization v.s. Memorization: Tracing Language Models' Capabilities Back to Pretraining Data","date":"2024-07-20","arxiv_id":"2407.14985","repositories_listed":0,"syntology":{"n":15,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/generalization-v-s-memorization-tracing#ran","syntology_url":"https://syntology.ai/paper/2407.14985","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.14985"}},"official":null}},{"url":null,"slug":"seal-advancing-speech-language-models-to-be","title":"Seal: Advancing Speech Language Models to be Few-Shot Learners","date":"2024-07-20","arxiv_id":"2407.14875","repositories_listed":0,"syntology":null},{"url":null,"slug":"contrastive-learning-with-counterfactual","title":"Contrastive Learning with Counterfactual Explanations for Radiology Report Generation","date":"2024-07-19","arxiv_id":"2407.14474","repositories_listed":0,"syntology":null},{"url":null,"slug":"cve-llm-automatic-vulnerability-evaluation-in","title":"CVE-LLM : Automatic vulnerability evaluation in medical device industry using large language models","date":"2024-07-19","arxiv_id":"2407.14640","repositories_listed":0,"syntology":null},{"url":null,"slug":"evlm-an-efficient-vision-language-model-for","title":"EVLM: An Efficient Vision-Language Model for Visual Understanding","date":"2024-07-19","arxiv_id":"2407.14177","repositories_listed":0,"syntology":null},{"url":null,"slug":"generative-language-model-for-catalyst","title":"Generative Language Model for Catalyst Discovery","date":"2024-07-19","arxiv_id":"2407.14040","repositories_listed":0,"syntology":null},{"url":null,"slug":"lamagic-language-model-based-topology","title":"LaMAGIC: Language-Model-based Topology Generation for Analog Integrated Circuits","date":"2024-07-19","arxiv_id":"2407.18269","repositories_listed":0,"syntology":null},{"url":null,"slug":"lapis-language-model-augmented-police","title":"LAPIS: Language Model-Augmented Police Investigation System","date":"2024-07-19","arxiv_id":"2407.20248","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-model-enabled-semantic","title":"Large Language Model Enabled Semantic Communication Systems","date":"2024-07-19","arxiv_id":"2407.14112","repositories_listed":0,"syntology":null},{"url":null,"slug":"llms-left-right-and-center-assessing-gpt-s","title":"LLMs left, right, and center: Assessing GPT's capabilities to label political bias from web domains","date":"2024-07-19","arxiv_id":"2407.14344","repositories_listed":0,"syntology":null},{"url":null,"slug":"mixture-of-experts-with-mixture-of-precisions","title":"Mixture of Experts with Mixture of Precisions for Tuning Quality of Service","date":"2024-07-19","arxiv_id":"2407.14417","repositories_listed":0,"syntology":null},{"url":null,"slug":"pd-tpe-parallel-decoder-with-text-guided","title":"PD-APE: A Parallel Decoding Framework with Adaptive Position Encoding for 3D Visual Grounding","date":"2024-07-19","arxiv_id":"2407.14491","repositories_listed":0,"syntology":null},{"url":null,"slug":"performance-modeling-and-workload-analysis-of","title":"Performance Modeling and Workload Analysis of Distributed Large Language Model Training and Inference","date":"2024-07-19","arxiv_id":"2407.14645","repositories_listed":0,"syntology":null},{"url":null,"slug":"semantic-cc-boosting-remote-sensing-image","title":"Semantic-CC: Boosting Remote Sensing Image Change Captioning via Foundational Knowledge and Semantic Guidance","date":"2024-07-19","arxiv_id":"2407.14032","repositories_listed":0,"syntology":null},{"url":null,"slug":"2408-00004","title":"Handling Numeric Expressions in Automatic Speech Recognition","date":"2024-07-18","arxiv_id":"2408.00004","repositories_listed":0,"syntology":null},{"url":null,"slug":"affordance-perception-by-a-knowledge-guided","title":"Affordance Perception by a Knowledge-Guided Vision-Language Model with Efficient Error Correction","date":"2024-07-18","arxiv_id":"2407.13368","repositories_listed":0,"syntology":null},{"url":null,"slug":"attention-overflow-language-model-input-blur","title":"Attention Overflow: Language Model Input Blur during Long-Context Missing Items Recommendation","date":"2024-07-18","arxiv_id":"2407.13481","repositories_listed":0,"syntology":null},{"url":null,"slug":"beaf-observing-before-after-changes-to","title":"BEAF: Observing BEfore-AFter Changes to Evaluate Hallucination in Vision-language Models","date":"2024-07-18","arxiv_id":"2407.13442","repositories_listed":0,"syntology":null},{"url":null,"slug":"combining-constraint-programming-reasoning","title":"Combining Constraint Programming Reasoning with Large Language Model Predictions","date":"2024-07-18","arxiv_id":"2407.13490","repositories_listed":0,"syntology":null},{"url":null,"slug":"correcting-the-mythos-of-kl-regularization","title":"Correcting the Mythos of KL-Regularization: Direct Alignment without Overoptimization via Chi-Squared Preference Optimization","date":"2024-07-18","arxiv_id":"2407.13399","repositories_listed":0,"syntology":null},{"url":null,"slug":"fantastic-sequences-and-where-to-find-them","title":"FANTAstic SEquences and Where to Find Them: Faithful and Efficient API Call Generation through State-tracked Constrained Decoding and Reranking","date":"2024-07-18","arxiv_id":"2407.13945","repositories_listed":0,"syntology":null},{"url":"/paper/fulg-150b-romanian-corpus-for-language-model","slug":"fulg-150b-romanian-corpus-for-language-model","title":"FuLG: 150B Romanian Corpus for Language Model Pretraining","date":"2024-07-18","arxiv_id":"2407.13657","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-visual-grounding-from-generative","title":"Learning Visual Grounding from Generative Vision and Language Model","date":"2024-07-18","arxiv_id":"2407.14563","repositories_listed":0,"syntology":null},{"url":null,"slug":"phi-3-safety-post-training-aligning-language","title":"Phi-3 Safety Post-Training: Aligning Language Models with a \"Break-Fix\" Cycle","date":"2024-07-18","arxiv_id":"2407.13833","repositories_listed":0,"syntology":null},{"url":null,"slug":"research-on-tibetan-tourism-viewpoints","title":"Research on Tibetan Tourism Viewpoints information generation system based on LLM","date":"2024-07-18","arxiv_id":"2407.13561","repositories_listed":0,"syntology":null},{"url":null,"slug":"rethinking-video-text-understanding-retrieval","title":"Rethinking Video-Text Understanding: Retrieval from Counterfactually Augmented Data","date":"2024-07-18","arxiv_id":"2407.13094","repositories_listed":0,"syntology":null},{"url":null,"slug":"segpoint-segment-any-point-cloud-via-large","title":"SegPoint: Segment Any Point Cloud via Large Language Model","date":"2024-07-18","arxiv_id":"2407.13761","repositories_listed":0,"syntology":null},{"url":null,"slug":"spontaneous-style-text-to-speech-synthesis","title":"Spontaneous Style Text-to-Speech Synthesis with Controllable Spontaneous Behaviors Based on Language Models","date":"2024-07-18","arxiv_id":"2407.13509","repositories_listed":0,"syntology":null},{"url":null,"slug":"transformer-based-single-cell-language-model","title":"Transformer-based Single-Cell Language Model: A Survey","date":"2024-07-18","arxiv_id":"2407.13205","repositories_listed":0,"syntology":null},{"url":null,"slug":"trialenroll-predicting-clinical-trial","title":"TrialEnroll: Predicting Clinical Trial Enrollment Success with Deep & Cross Network and Large Language Models","date":"2024-07-18","arxiv_id":"2407.13115","repositories_listed":0,"syntology":null},{"url":null,"slug":"conversational-query-reformulation-with-the","title":"Conversational Query Reformulation with the Guidance of Retrieved Documents","date":"2024-07-17","arxiv_id":"2407.12363","repositories_listed":0,"syntology":null}],"record_sha256":"864b75ec75402c9a858543221454195ea0e3b6bc898b355cc1613eba75443370","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}