{"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/78","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":78,"pages_in_order":142,"rows_per_page":100,"rows":[7701,7800],"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/77","next":"/task/language-modeling/papers/79","papers":[{"url":null,"slug":"to-err-is-ai-a-case-study-informing-llm-flaw","title":"To Err is AI : A Case Study Informing LLM Flaw Reporting Practices","date":"2024-10-15","arxiv_id":"2410.12104","repositories_listed":0,"syntology":null},{"url":null,"slug":"tokenization-and-morphology-in-multilingual","title":"Tokenization and Morphology in Multilingual Language Models: A Comparative Analysis of mT5 and ByT5","date":"2024-10-15","arxiv_id":"2410.11627","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-more-effective-table-to-text","title":"Towards More Effective Table-to-Text Generation: Assessing In-Context Learning and Self-Evaluation with Open-Source Models","date":"2024-10-15","arxiv_id":"2410.12878","repositories_listed":0,"syntology":null},{"url":null,"slug":"y-mol-a-multiscale-biomedical-knowledge","title":"Y-Mol: A Multiscale Biomedical Knowledge-Guided Large Language Model for Drug Development","date":"2024-10-15","arxiv_id":"2410.11550","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-multi-task-text-classification-pipeline","title":"A Multi-Task Text Classification Pipeline with Natural Language Explanations: A User-Centric Evaluation in Sentiment Analysis and Offensive Language Identification in Greek Tweets","date":"2024-10-14","arxiv_id":"2410.10290","repositories_listed":0,"syntology":null},{"url":null,"slug":"beyond-right-and-wrong-mitigating-cold-start","title":"Not All Options Are Created Equal: Textual Option Weighting for Token-Efficient LLM-Based Knowledge Tracing","date":"2024-10-14","arxiv_id":"2410.12872","repositories_listed":0,"syntology":null},{"url":null,"slug":"forgerygpt-multimodal-large-language-model","title":"ForgeryGPT: Multimodal Large Language Model For Explainable Image Forgery Detection and Localization","date":"2024-10-14","arxiv_id":"2410.10238","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-model-enhanced-reinforcement","title":"Large Language Model-Enhanced Reinforcement Learning for Generic Bus Holding Control Strategies","date":"2024-10-14","arxiv_id":"2410.10212","repositories_listed":0,"syntology":null},{"url":null,"slug":"lg-cav-train-any-concept-activation-vector","title":"LG-CAV: Train Any Concept Activation Vector with Language Guidance","date":"2024-10-14","arxiv_id":"2410.10308","repositories_listed":0,"syntology":null},{"url":null,"slug":"lobg-less-overfitting-for-better","title":"LOBG:Less Overfitting for Better Generalization in Vision-Language Model","date":"2024-10-14","arxiv_id":"2410.10247","repositories_listed":0,"syntology":null},{"url":null,"slug":"model-based-differentially-private-knowledge","title":"Model-based Large Language Model Customization as Service","date":"2024-10-14","arxiv_id":"2410.10481","repositories_listed":0,"syntology":null},{"url":null,"slug":"recipe-for-zero-shot-pos-tagging-is-it-useful","title":"Recipe for Zero-shot POS Tagging: Is It Useful in Realistic Scenarios?","date":"2024-10-14","arxiv_id":"2410.10576","repositories_listed":0,"syntology":null},{"url":null,"slug":"skill-learning-using-process-mining-for-large","title":"Skill Learning Using Process Mining for Large Language Model Plan Generation","date":"2024-10-14","arxiv_id":"2410.12870","repositories_listed":0,"syntology":null},{"url":null,"slug":"unified-representation-of-genomic-and","title":"Unified Representation of Genomic and Biomedical Concepts through Multi-Task, Multi-Source Contrastive Learning","date":"2024-10-14","arxiv_id":"2410.10144","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-reasoning-and-acting-in-medical","title":"Adaptive Reasoning and Acting in Medical Language Agents","date":"2024-10-13","arxiv_id":"2410.10020","repositories_listed":0,"syntology":null},{"url":null,"slug":"collu-bench-a-benchmark-for-predicting","title":"Collu-Bench: A Benchmark for Predicting Language Model Hallucinations in Code","date":"2024-10-13","arxiv_id":"2410.09997","repositories_listed":0,"syntology":null},{"url":null,"slug":"echoprime-a-multi-video-view-informed-vision","title":"EchoPrime: A Multi-Video View-Informed Vision-Language Model for Comprehensive Echocardiography Interpretation","date":"2024-10-13","arxiv_id":"2410.09704","repositories_listed":0,"syntology":null},{"url":null,"slug":"generating-driving-simulations-via","title":"Conversational Code Generation: a Case Study of Designing a Dialogue System for Generating Driving Scenarios for Testing Autonomous Vehicles","date":"2024-10-13","arxiv_id":"2410.09829","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-rank-for-multiple-retrieval","title":"Learning to Rank for Multiple Retrieval-Augmented Models through Iterative Utility Maximization","date":"2024-10-13","arxiv_id":"2410.09942","repositories_listed":0,"syntology":null},{"url":null,"slug":"lore-logit-ranked-retriever-ensemble-for","title":"LoRE: Logit-Ranked Retriever Ensemble for Enhancing Open-Domain Question Answering","date":"2024-10-13","arxiv_id":"2410.10042","repositories_listed":0,"syntology":null},{"url":null,"slug":"moin-mixture-of-introvert-experts-to-upcycle","title":"MoIN: Mixture of Introvert Experts to Upcycle an LLM","date":"2024-10-13","arxiv_id":"2410.09687","repositories_listed":0,"syntology":null},{"url":null,"slug":"impeding-llm-assisted-cheating-in","title":"Impeding LLM-assisted Cheating in Introductory Programming Assignments via Adversarial Perturbation","date":"2024-10-12","arxiv_id":"2410.09318","repositories_listed":0,"syntology":null},{"url":null,"slug":"acer-automatic-language-model-context","title":"ACER: Automatic Language Model Context Extension via Retrieval","date":"2024-10-11","arxiv_id":"2410.09141","repositories_listed":0,"syntology":null},{"url":null,"slug":"aerial-vision-and-language-navigation-via","title":"Aerial Vision-and-Language Navigation via Semantic-Topo-Metric Representation Guided LLM Reasoning","date":"2024-10-11","arxiv_id":"2410.08500","repositories_listed":0,"syntology":null},{"url":null,"slug":"calibrated-cache-model-for-few-shot-vision","title":"Calibrated Cache Model for Few-Shot Vision-Language Model Adaptation","date":"2024-10-11","arxiv_id":"2410.08895","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficiently-scanning-and-resampling-spatio","title":"Efficiently Scanning and Resampling Spatio-Temporal Tasks with Irregular Observations","date":"2024-10-11","arxiv_id":"2410.08681","repositories_listed":0,"syntology":null},{"url":null,"slug":"forall-uto-exists-lor-land-l-autonomous","title":"$\\forall$uto$\\exists$$\\lor\\!\\land$L: Autonomous Evaluation of LLMs for Truth Maintenance and Reasoning Tasks","date":"2024-10-11","arxiv_id":"2410.08437","repositories_listed":0,"syntology":null},{"url":null,"slug":"hypothesis-only-biases-in-large-language","title":"Hypothesis-only Biases in Large Language Model-Elicited Natural Language Inference","date":"2024-10-11","arxiv_id":"2410.08996","repositories_listed":0,"syntology":null},{"url":null,"slug":"language-model-assisted-bi-level-programming","title":"Language-Model-Assisted Bi-Level Programming for Reward Learning from Internet Videos","date":"2024-10-11","arxiv_id":"2410.09286","repositories_listed":0,"syntology":null},{"url":null,"slug":"lifelong-event-detection-via-optimal","title":"Lifelong Event Detection via Optimal Transport","date":"2024-10-11","arxiv_id":"2410.08905","repositories_listed":0,"syntology":null},{"url":null,"slug":"llmd-a-large-language-model-for-interpreting","title":"LLMD: A Large Language Model for Interpreting Longitudinal Medical Records","date":"2024-10-11","arxiv_id":"2410.12860","repositories_listed":0,"syntology":null},{"url":null,"slug":"nach0-pc-multi-task-language-model-with","title":"nach0-pc: Multi-task Language Model with Molecular Point Cloud Encoder","date":"2024-10-11","arxiv_id":"2410.09240","repositories_listed":0,"syntology":null},{"url":null,"slug":"preferential-normalizing-flows","title":"Preferential Normalizing Flows","date":"2024-10-11","arxiv_id":"2410.08710","repositories_listed":0,"syntology":null},{"url":null,"slug":"simplestrat-diversifying-language-model","title":"SimpleStrat: Diversifying Language Model Generation with Stratification","date":"2024-10-11","arxiv_id":"2410.09038","repositories_listed":0,"syntology":null},{"url":null,"slug":"simultaneous-reward-distillation-and","title":"Simultaneous Reward Distillation and Preference Learning: Get You a Language Model Who Can Do Both","date":"2024-10-11","arxiv_id":"2410.08458","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-dynamics-of-social-conventions-in-llm","title":"Emergent social conventions and collective bias in LLM populations","date":"2024-10-11","arxiv_id":"2410.08948","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-same-but-different-structural","title":"The Same But Different: Structural Similarities and Differences in Multilingual Language Modeling","date":"2024-10-11","arxiv_id":"2410.09223","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-trustworthy-knowledge-graph-reasoning","title":"Towards Trustworthy Knowledge Graph Reasoning: An Uncertainty Aware Perspective","date":"2024-10-11","arxiv_id":"2410.08985","repositories_listed":0,"syntology":null},{"url":null,"slug":"vit3d-alignment-of-llama3-3d-medical-image","title":"ViT3D Alignment of LLaMA3: 3D Medical Image Report Generation","date":"2024-10-11","arxiv_id":"2410.08588","repositories_listed":0,"syntology":null},{"url":null,"slug":"vlm-see-robot-do-human-demo-video-to-robot","title":"VLM See, Robot Do: Human Demo Video to Robot Action Plan via Vision Language Model","date":"2024-10-11","arxiv_id":"2410.08792","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-framework-for-collaborating-a-large","title":"A Framework for Collaborating a Large Language Model Tool in Brainstorming for Triggering Creative Thoughts","date":"2024-10-10","arxiv_id":"2410.11877","repositories_listed":0,"syntology":null},{"url":null,"slug":"crossquant-a-post-training-quantization","title":"CrossQuant: A Post-Training Quantization Method with Smaller Quantization Kernel for Precise Large Language Model Compression","date":"2024-10-10","arxiv_id":"2410.07505","repositories_listed":0,"syntology":null},{"url":null,"slug":"dice-discrete-inversion-enabling-controllable","title":"DICE: Discrete Inversion Enabling Controllable Editing for Multinomial Diffusion and Masked Generative Models","date":"2024-10-10","arxiv_id":"2410.08207","repositories_listed":0,"syntology":null},{"url":null,"slug":"disease-entity-recognition-and-normalization","title":"Disease Entity Recognition and Normalization is Improved with Large Language Model Derived Synthetic Normalized Mentions","date":"2024-10-10","arxiv_id":"2410.07951","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-reinforcement-learning-with-large","title":"Efficient Reinforcement Learning with Large Language Model Priors","date":"2024-10-10","arxiv_id":"2410.07927","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-language-model-reasoning-via","title":"Semantic Self-Consistency: Enhancing Language Model Reasoning via Semantic Weighting","date":"2024-10-10","arxiv_id":"2410.07839","repositories_listed":0,"syntology":null},{"url":null,"slug":"evolutionary-contrastive-distillation-for","title":"Evolutionary Contrastive Distillation for Language Model Alignment","date":"2024-10-10","arxiv_id":"2410.07513","repositories_listed":0,"syntology":null},{"url":null,"slug":"language-model-developers-should-report-train","title":"Language model developers should report train-test overlap","date":"2024-10-10","arxiv_id":"2410.08385","repositories_listed":0,"syntology":null},{"url":null,"slug":"lecprompt-a-prompt-based-approach-for-logical","title":"LecPrompt: A Prompt-based Approach for Logical Error Correction with CodeBERT","date":"2024-10-10","arxiv_id":"2410.08241","repositories_listed":0,"syntology":null},{"url":null,"slug":"mechanistic-permutability-match-features","title":"Mechanistic Permutability: Match Features Across Layers","date":"2024-10-10","arxiv_id":"2410.07656","repositories_listed":0,"syntology":null},{"url":null,"slug":"plamo-100b-a-ground-up-language-model","title":"PLaMo-100B: A Ground-Up Language Model Designed for Japanese Proficiency","date":"2024-10-10","arxiv_id":"2410.07563","repositories_listed":0,"syntology":null},{"url":null,"slug":"sample-then-identify-a-general-framework-for","title":"Sample then Identify: A General Framework for Risk Control and Assessment in Multimodal Large Language Models","date":"2024-10-10","arxiv_id":"2410.08174","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-large-language-model-greeklegalroberta","title":"The Large Language Model GreekLegalRoBERTa","date":"2024-10-10","arxiv_id":"2410.12852","repositories_listed":0,"syntology":null},{"url":null,"slug":"uncovering-overfitting-in-large-language","title":"Uncovering Overfitting in Large Language Model Editing","date":"2024-10-10","arxiv_id":"2410.07819","repositories_listed":0,"syntology":null},{"url":null,"slug":"b-calibration-of-language-model-confidence","title":"$β$-calibration of Language Model Confidence Scores for Generative QA","date":"2024-10-09","arxiv_id":"2410.06615","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-efficient-foundational-multi-modal","title":"Exploring Efficient Foundational Multi-modal Models for Video Summarization","date":"2024-10-09","arxiv_id":"2410.07405","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-prompt-engineering-a-systematic","title":"Exploring Prompt Engineering: A Systematic Review with SWOT Analysis","date":"2024-10-09","arxiv_id":"2410.12843","repositories_listed":0,"syntology":null},{"url":null,"slug":"fltlm-an-intergrated-long-context-large","title":"FltLM: An Intergrated Long-Context Large Language Model for Effective Context Filtering and Understanding","date":"2024-10-09","arxiv_id":"2410.06886","repositories_listed":0,"syntology":null},{"url":null,"slug":"generating-long-horizon-stock-buy-signals","title":"Generating long-horizon stock \"buy\" signals with a neural language model","date":"2024-10-09","arxiv_id":"2410.18988","repositories_listed":0,"syntology":null},{"url":null,"slug":"let-s-ask-gnn-empowering-large-language-model","title":"Let's Ask GNN: Empowering Large Language Model for Graph In-Context Learning","date":"2024-10-09","arxiv_id":"2410.07074","repositories_listed":0,"syntology":null},{"url":null,"slug":"llm-compression-with-neural-architecture","title":"Large Language Model Compression with Neural Architecture Search","date":"2024-10-09","arxiv_id":"2410.06479","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-task-program-error-repair-and","title":"Multi-Task Program Error Repair and Explanatory Diagnosis","date":"2024-10-09","arxiv_id":"2410.07271","repositories_listed":0,"syntology":null},{"url":null,"slug":"personal-intelligence-system-unilm-hybrid-on","title":"Personal Intelligence System UniLM: Hybrid On-Device Small Language Model and Server-Based Large Language Model for Malay Nusantara","date":"2024-10-09","arxiv_id":"2410.06973","repositories_listed":0,"syntology":null},{"url":null,"slug":"quailora-quantization-aware-initialization","title":"QuAILoRA: Quantization-Aware Initialization for LoRA","date":"2024-10-09","arxiv_id":"2410.14713","repositories_listed":0,"syntology":null},{"url":null,"slug":"recent-advancements-in-llm-red-teaming","title":"Recent advancements in LLM Red-Teaming: Techniques, Defenses, and Ethical Considerations","date":"2024-10-09","arxiv_id":"2410.09097","repositories_listed":0,"syntology":null},{"url":null,"slug":"reproducing-and-extending-experiments-in","title":"Reproducing and Extending Experiments in Behavioral Strategy with Large Language Models","date":"2024-10-09","arxiv_id":"2410.06932","repositories_listed":0,"syntology":null},{"url":null,"slug":"stuffed-mamba-state-collapse-and-state","title":"Stuffed Mamba: State Collapse and State Capacity of RNN-Based Long-Context Modeling","date":"2024-10-09","arxiv_id":"2410.07145","repositories_listed":0,"syntology":null},{"url":null,"slug":"tinyclick-single-turn-agent-for-empowering","title":"TinyClick: Single-Turn Agent for Empowering GUI Automation","date":"2024-10-09","arxiv_id":"2410.11871","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-universality-studying-mechanistic","title":"Towards Universality: Studying Mechanistic Similarity Across Language Model Architectures","date":"2024-10-09","arxiv_id":"2410.06672","repositories_listed":0,"syntology":null},{"url":null,"slug":"accelerated-preference-optimization-for-large","title":"Accelerated Preference Optimization for Large Language Model Alignment","date":"2024-10-08","arxiv_id":"2410.06293","repositories_listed":0,"syntology":null},{"url":null,"slug":"application-of-notebooklm-a-large-language","title":"Application of NotebookLM, a Large Language Model with Retrieval-Augmented Generation, for Lung Cancer Staging","date":"2024-10-08","arxiv_id":"2410.10869","repositories_listed":0,"syntology":null},{"url":null,"slug":"applying-refusal-vector-ablation-to-llama-3-1","title":"Applying Refusal-Vector Ablation to Llama 3.1 70B Agents","date":"2024-10-08","arxiv_id":"2410.10871","repositories_listed":0,"syntology":null},{"url":null,"slug":"claimbrush-a-novel-framework-for-automated","title":"ClaimBrush: A Novel Framework for Automated Patent Claim Refinement Based on Large Language Models","date":"2024-10-08","arxiv_id":"2410.05575","repositories_listed":0,"syntology":null},{"url":null,"slug":"decoratelm-data-engineering-through-corpus","title":"DecorateLM: Data Engineering through Corpus Rating, Tagging, and Editing with Language Models","date":"2024-10-08","arxiv_id":"2410.05639","repositories_listed":0,"syntology":null},{"url":null,"slug":"fine-grained-hallucination-detection-and-2","title":"FG-PRM: Fine-grained Hallucination Detection and Mitigation in Language Model Mathematical Reasoning","date":"2024-10-08","arxiv_id":"2410.06304","repositories_listed":0,"syntology":null},{"url":null,"slug":"jet-expansions-of-residual-computation","title":"Jet Expansions of Residual Computation","date":"2024-10-08","arxiv_id":"2410.06024","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-session-client-centered-treatment","title":"Multi-Session Client-Centered Treatment Outcome Evaluation in Psychotherapy","date":"2024-10-08","arxiv_id":"2410.05824","repositories_listed":0,"syntology":null},{"url":null,"slug":"parallelspec-parallel-drafter-for-efficient","title":"ParallelSpec: Parallel Drafter for Efficient Speculative Decoding","date":"2024-10-08","arxiv_id":"2410.05589","repositories_listed":0,"syntology":null},{"url":null,"slug":"retrieving-rethinking-and-revising-the-chain","title":"Retrieving, Rethinking and Revising: The Chain-of-Verification Can Improve Retrieval Augmented Generation","date":"2024-10-08","arxiv_id":"2410.05801","repositories_listed":0,"syntology":null},{"url":null,"slug":"activation-scaling-for-steering-and","title":"Activation Scaling for Steering and Interpreting Language Models","date":"2024-10-07","arxiv_id":"2410.04962","repositories_listed":0,"syntology":null},{"url":null,"slug":"chain-and-causal-attention-for-efficient","title":"Chain and Causal Attention for Efficient Entity Tracking","date":"2024-10-07","arxiv_id":"2410.05565","repositories_listed":0,"syntology":null},{"url":null,"slug":"constructing-and-masking-preference-profile","title":"Filtering Discomforting Recommendations with Large Language Models","date":"2024-10-07","arxiv_id":"2410.05411","repositories_listed":0,"syntology":null},{"url":null,"slug":"dept-decoupled-embeddings-for-pre-training","title":"DEPT: Decoupled Embeddings for Pre-training Language Models","date":"2024-10-07","arxiv_id":"2410.05021","repositories_listed":0,"syntology":null},{"url":null,"slug":"driving-with-regulation-interpretable","title":"Driving with Regulation: Interpretable Decision-Making for Autonomous Vehicles with Retrieval-Augmented Reasoning via LLM","date":"2024-10-07","arxiv_id":"2410.04759","repositories_listed":0,"syntology":null},{"url":null,"slug":"falcon-mamba-the-first-competitive-attention","title":"Falcon Mamba: The First Competitive Attention-free 7B Language Model","date":"2024-10-07","arxiv_id":"2410.05355","repositories_listed":0,"syntology":null},{"url":null,"slug":"leverage-knowledge-graph-and-large-language","title":"Leverage Knowledge Graph and Large Language Model for Law Article Recommendation: A Case Study of Chinese Criminal Law","date":"2024-10-07","arxiv_id":"2410.04949","repositories_listed":0,"syntology":null},{"url":null,"slug":"lpzero-language-model-zero-cost-proxy-search","title":"LPZero: Language Model Zero-cost Proxy Search from Zero","date":"2024-10-07","arxiv_id":"2410.04808","repositories_listed":0,"syntology":null},{"url":null,"slug":"reasoning-paths-optimization-learning-to","title":"Reasoning Paths Optimization: Learning to Reason and Explore From Diverse Paths","date":"2024-10-07","arxiv_id":"2410.10858","repositories_listed":0,"syntology":null},{"url":null,"slug":"respllm-unifying-audio-and-text-with","title":"RespLLM: Unifying Audio and Text with Multimodal LLMs for Generalized Respiratory Health Prediction","date":"2024-10-07","arxiv_id":"2410.05361","repositories_listed":0,"syntology":null},{"url":null,"slug":"sftmix-elevating-language-model-instruction","title":"SFTMix: Elevating Language Model Instruction Tuning with Mixup Recipe","date":"2024-10-07","arxiv_id":"2410.05248","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-the-generation-of-hierarchical-attack","title":"Towards the generation of hierarchical attack models from cybersecurity vulnerabilities using language models","date":"2024-10-07","arxiv_id":"2410.05351","repositories_listed":0,"syntology":null},{"url":null,"slug":"transformers-learn-variable-order-markov","title":"Transformers learn variable-order Markov chains in-context","date":"2024-10-07","arxiv_id":"2410.05493","repositories_listed":0,"syntology":null},{"url":null,"slug":"vlm2vec-training-vision-language-models-for","title":"VLM2Vec: Training Vision-Language Models for Massive Multimodal Embedding Tasks","date":"2024-10-07","arxiv_id":"2410.05160","repositories_listed":0,"syntology":null},{"url":null,"slug":"wireless-friendly-window-position","title":"Wireless-Friendly Window Position Optimization for RIS-Aided Outdoor-to-Indoor Networks based on Multi-Modal Large Language Model","date":"2024-10-07","arxiv_id":"2410.20691","repositories_listed":0,"syntology":null},{"url":null,"slug":"hall-e-hierarchical-neural-codec-language","title":"HALL-E: Hierarchical Neural Codec Language Model for Minute-Long Zero-Shot Text-to-Speech Synthesis","date":"2024-10-06","arxiv_id":"2410.04380","repositories_listed":0,"syntology":null},{"url":null,"slug":"od-stega-llm-based-near-imperceptible","title":"OD-Stega: LLM-Based Near-Imperceptible Steganography via Optimized Distributions","date":"2024-10-06","arxiv_id":"2410.04328","repositories_listed":0,"syntology":null},{"url":null,"slug":"retok-replacing-tokenizer-to-enhance","title":"ReTok: Replacing Tokenizer to Enhance Representation Efficiency in Large Language Model","date":"2024-10-06","arxiv_id":"2410.04335","repositories_listed":0,"syntology":null},{"url":"/paper/adaptive-question-answering-enhancing","slug":"adaptive-question-answering-enhancing","title":"Adaptive Question Answering: Enhancing Language Model Proficiency for Addressing Knowledge Conflicts with Source Citations","date":"2024-10-05","arxiv_id":"2410.04241","repositories_listed":0,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/adaptive-question-answering-enhancing#ran","syntology_url":"https://syntology.ai/paper/2410.04241","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.04241"}},"official":null}},{"url":null,"slug":"assessing-the-performance-of-human-capable","title":"Assessing the Performance of Human-Capable LLMs -- Are LLMs Coming for Your Job?","date":"2024-10-05","arxiv_id":"2410.16285","repositories_listed":0,"syntology":null},{"url":null,"slug":"language-model-driven-data-pruning-enables","title":"Language Model-Driven Data Pruning Enables Efficient Active Learning","date":"2024-10-05","arxiv_id":"2410.04275","repositories_listed":0,"syntology":null}],"record_sha256":"71e32e24a92b1ad9e15ef66c9eff2af0de275a9c911743ef780970af4da8b3ac","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}