{"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/93","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":93,"pages_in_order":177,"rows_per_page":100,"rows":[9201,9300],"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/92","next":"/task/language-modelling/papers/94","papers":[{"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":"promptly-yours-a-human-subject-study-on","title":"Promptly Yours? A Human Subject Study on Prompt Inference in AI-Generated Art","date":"2024-10-10","arxiv_id":"2410.08406","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":"boosting-few-shot-detection-with-large","title":"Boosting Few-Shot Detection with Large Language Models and Layout-to-Image Synthesis","date":"2024-10-09","arxiv_id":"2410.06841","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":"uncovering-factor-level-preferences-to","title":"Uncovering Factor Level Preferences to Improve Human-Model Alignment","date":"2024-10-09","arxiv_id":"2410.06965","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":"taptype-ten-finger-text-entry-on-everyday","title":"TapType: Ten-finger text entry on everyday surfaces via Bayesian inference","date":"2024-10-08","arxiv_id":"2410.06001","repositories_listed":0,"syntology":null},{"url":null,"slug":"teasergen-generating-teasers-for-long","title":"TeaserGen: Generating Teasers for Long Documentaries","date":"2024-10-08","arxiv_id":"2410.05586","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":"in-the-loop-hyper-parameter-optimization-for","title":"In-the-loop Hyper-Parameter Optimization for LLM-Based Automated Design of Heuristics","date":"2024-10-07","arxiv_id":"2410.16309","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-how-hard-to-think-input-adaptive","title":"Learning How Hard to Think: Input-Adaptive Allocation of LM Computation","date":"2024-10-07","arxiv_id":"2410.04707","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},{"url":null,"slug":"roqllama-a-lightweight-romanian-adapted","title":"RoQLlama: A Lightweight Romanian Adapted Language Model","date":"2024-10-05","arxiv_id":"2410.04269","repositories_listed":0,"syntology":null},{"url":null,"slug":"toxic-subword-pruning-for-dialogue-response","title":"Toxic Subword Pruning for Dialogue Response Generation on Large Language Models","date":"2024-10-05","arxiv_id":"2410.04155","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-large-language-model-based-framework-for","title":"A Large Language Model-based Framework for Semi-Structured Tender Document Retrieval-Augmented Generation","date":"2024-10-04","arxiv_id":"2410.09077","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-x-ray-is-worth-15-features-sparse","title":"An X-Ray Is Worth 15 Features: Sparse Autoencoders for Interpretable Radiology Report Generation","date":"2024-10-04","arxiv_id":"2410.03334","repositories_listed":0,"syntology":null},{"url":null,"slug":"audio-agent-leveraging-llms-for-audio","title":"Audio-Agent: Leveraging LLMs For Audio Generation, Editing and Composition","date":"2024-10-04","arxiv_id":"2410.03335","repositories_listed":0,"syntology":null},{"url":null,"slug":"autoregressive-large-language-models-are","title":"Autoregressive Large Language Models are Computationally Universal","date":"2024-10-04","arxiv_id":"2410.03170","repositories_listed":0,"syntology":null},{"url":null,"slug":"conditional-enzyme-generation-using-protein","title":"Function-Guided Conditional Generation Using Protein Language Models with Adapters","date":"2024-10-04","arxiv_id":"2410.03634","repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-lingual-transfer-for-automatic-question","title":"Cross-lingual Transfer for Automatic Question Generation by Learning Interrogative Structures in Target Languages","date":"2024-10-04","arxiv_id":"2410.03197","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-short-text-topic-modeling-with-llm","title":"Enhancing Short-Text Topic Modeling with LLM-Driven Context Expansion and Prefix-Tuned VAEs","date":"2024-10-04","arxiv_id":"2410.03071","repositories_listed":0,"syntology":null},{"url":null,"slug":"image-first-or-text-first-optimising-the","title":"Image First or Text First? Optimising the Sequencing of Modalities in Large Language Model Prompting and Reasoning Tasks","date":"2024-10-04","arxiv_id":"2410.03062","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-model-performance-benchmarking","title":"Understanding Large Language Models in Your Pockets: Performance Study on COTS Mobile Devices","date":"2024-10-04","arxiv_id":"2410.03613","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-models-can-be-strong-self","title":"Large Language Models can be Strong Self-Detoxifiers","date":"2024-10-04","arxiv_id":"2410.03818","repositories_listed":0,"syntology":null},{"url":null,"slug":"no-need-to-talk-asynchronous-mixture-of","title":"No Need to Talk: Asynchronous Mixture of Language Models","date":"2024-10-04","arxiv_id":"2410.03529","repositories_listed":0,"syntology":null},{"url":null,"slug":"parallel-corpus-augmentation-using-masked","title":"Parallel Corpus Augmentation using Masked Language Models","date":"2024-10-04","arxiv_id":"2410.03194","repositories_listed":0,"syntology":null},{"url":null,"slug":"permissive-information-flow-analysis-for","title":"Permissive Information-Flow Analysis for Large Language Models","date":"2024-10-04","arxiv_id":"2410.03055","repositories_listed":0,"syntology":null},{"url":null,"slug":"scaling-parameter-constrained-language-models","title":"Scaling Parameter-Constrained Language Models with Quality Data","date":"2024-10-04","arxiv_id":"2410.03083","repositories_listed":0,"syntology":null},{"url":null,"slug":"surgical-cheap-and-flexible-mitigating-false","title":"Surgical, Cheap, and Flexible: Mitigating False Refusal in Language Models via Single Vector Ablation","date":"2024-10-04","arxiv_id":"2410.03415","repositories_listed":0,"syntology":null},{"url":null,"slug":"textless-streaming-speech-to-speech","title":"Textless Streaming Speech-to-Speech Translation using Semantic Speech Tokens","date":"2024-10-04","arxiv_id":"2410.03298","repositories_listed":0,"syntology":null},{"url":null,"slug":"uncomp-uncertainty-aware-long-context","title":"UNComp: Uncertainty-Aware Long-Context Compressor for Efficient Large Language Model Inference","date":"2024-10-04","arxiv_id":"2410.03090","repositories_listed":0,"syntology":null},{"url":null,"slug":"using-prompts-to-guide-large-language-models","title":"Using Prompts to Guide Large Language Models in Imitating a Real Person's Language Style","date":"2024-10-04","arxiv_id":"2410.03848","repositories_listed":0,"syntology":null},{"url":null,"slug":"better-call-saul-fluent-and-consistent","title":"Better Call SAUL: Fluent and Consistent Language Model Editing with Generation Regularization","date":"2024-10-03","arxiv_id":"2410.02433","repositories_listed":0,"syntology":null},{"url":null,"slug":"braintransformers-snn-llm","title":"BrainTransformers: SNN-LLM","date":"2024-10-03","arxiv_id":"2410.14687","repositories_listed":0,"syntology":null},{"url":null,"slug":"calmflow-volterra-flow-matching-using-causal","title":"CaLMFlow: Volterra Flow Matching using Causal Language Models","date":"2024-10-03","arxiv_id":"2410.05292","repositories_listed":0,"syntology":null},{"url":null,"slug":"codepmp-scalable-preference-model-pretraining","title":"CodePMP: Scalable Preference Model Pretraining for Large Language Model Reasoning","date":"2024-10-03","arxiv_id":"2410.02229","repositories_listed":0,"syntology":null},{"url":null,"slug":"computational-modeling-of-artistic","title":"Computational Modeling of Artistic Inspiration: A Framework for Predicting Aesthetic Preferences in Lyrical Lines Using Linguistic and Stylistic Features","date":"2024-10-03","arxiv_id":"2410.02881","repositories_listed":0,"syntology":null},{"url":null,"slug":"cut-the-crap-an-economical-communication","title":"Cut the Crap: An Economical Communication Pipeline for LLM-based Multi-Agent Systems","date":"2024-10-03","arxiv_id":"2410.02506","repositories_listed":0,"syntology":null},{"url":null,"slug":"determine-then-ensemble-necessity-of-top-k","title":"Determine-Then-Ensemble: Necessity of Top-k Union for Large Language Model Ensembling","date":"2024-10-03","arxiv_id":"2410.03777","repositories_listed":0,"syntology":null},{"url":null,"slug":"geometry-is-all-you-need-a-unified-taxonomy","title":"Geometry is All You Need: A Unified Taxonomy of Matrix and Tensor Factorization for Compression of Generative Language Models","date":"2024-10-03","arxiv_id":"2410.03040","repositories_listed":0,"syntology":null},{"url":null,"slug":"grounding-large-language-models-in-embodied","title":"Grounding Large Language Models In Embodied Environment With Imperfect World Models","date":"2024-10-03","arxiv_id":"2410.02742","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-model-aided-multi-objective","title":"Large Language Model Aided Multi-objective Evolutionary Algorithm: a Low-cost Adaptive Approach","date":"2024-10-03","arxiv_id":"2410.02301","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-model-for-multi-domain","title":"Large Language Model for Multi-Domain Translation: Benchmarking and Domain CoT Fine-tuning","date":"2024-10-03","arxiv_id":"2410.02631","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-the-latent-rules-of-a-game-from-data","title":"Learning the Latent Rules of a Game from Data: A Chess Story","date":"2024-10-03","arxiv_id":"2410.02426","repositories_listed":0,"syntology":null},{"url":null,"slug":"llmco2-advancing-accurate-carbon-footprint","title":"LLMCO2: Advancing Accurate Carbon Footprint Prediction for LLM Inferences","date":"2024-10-03","arxiv_id":"2410.02950","repositories_listed":0,"syntology":null},{"url":null,"slug":"logra-med-long-context-multi-graph-alignment","title":"LoGra-Med: Long Context Multi-Graph Alignment for Medical Vision-Language Model","date":"2024-10-03","arxiv_id":"2410.02615","repositories_listed":0,"syntology":null},{"url":null,"slug":"medvisionllama-leveraging-pre-trained-large","title":"MedVisionLlama: Leveraging Pre-Trained Large Language Model Layers to Enhance Medical Image Segmentation","date":"2024-10-03","arxiv_id":"2410.02458","repositories_listed":0,"syntology":null},{"url":null,"slug":"morphological-evaluation-of-subwords","title":"Morphological evaluation of subwords vocabulary used by BETO language model","date":"2024-10-03","arxiv_id":"2410.02283","repositories_listed":0,"syntology":null}],"record_sha256":"212f52b110f98adc23cebf0b9007dd18fa0a17cb5337ec91d7a35feeb0469c85","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}