{"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/100","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":100,"pages_in_order":142,"rows_per_page":100,"rows":[9901,10000],"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/99","next":"/task/language-modeling/papers/101","papers":[{"url":null,"slug":"frontier-language-models-are-not-robust-to","title":"Frontier Language Models are not Robust to Adversarial Arithmetic, or \"What do I need to say so you agree 2+2=5?","date":"2023-11-08","arxiv_id":"2311.07587","repositories_listed":0,"syntology":null},{"url":null,"slug":"ai-for-all-operationalising-diversity-and","title":"AI for All: Operationalising Diversity and Inclusion Requirements for AI Systems","date":"2023-11-07","arxiv_id":"2311.14695","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-the-effectiveness-of-retrieval","title":"Evaluating the Effectiveness of Retrieval-Augmented Large Language Models in Scientific Document Reasoning","date":"2023-11-07","arxiv_id":"2311.04348","repositories_listed":0,"syntology":null},{"url":null,"slug":"formal-aspects-of-language-modeling","title":"Formal Aspects of Language Modeling","date":"2023-11-07","arxiv_id":"2311.04329","repositories_listed":0,"syntology":null},{"url":null,"slug":"olala-ontology-matching-with-large-language","title":"OLaLa: Ontology Matching with Large Language Models","date":"2023-11-07","arxiv_id":"2311.03837","repositories_listed":0,"syntology":null},{"url":null,"slug":"dail-data-augmentation-for-in-context","title":"DAIL: Data Augmentation for In-Context Learning via Self-Paraphrase","date":"2023-11-06","arxiv_id":"2311.03319","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-high-level-synthesis-and-large","title":"Leveraging High-Level Synthesis and Large Language Models to Generate, Simulate, and Deploy a Uniform Random Number Generator Hardware Design","date":"2023-11-06","arxiv_id":"2311.03489","repositories_listed":0,"syntology":null},{"url":null,"slug":"propath-disease-specific-protein-language","title":"ProPath: Disease-Specific Protein Language Model for Variant Pathogenicity","date":"2023-11-06","arxiv_id":"2311.03429","repositories_listed":0,"syntology":null},{"url":null,"slug":"scalable-and-transferable-black-box","title":"Scalable and Transferable Black-Box Jailbreaks for Language Models via Persona Modulation","date":"2023-11-06","arxiv_id":"2311.03348","repositories_listed":0,"syntology":null},{"url":null,"slug":"circle-multi-turn-query-clarifications-with","title":"CIRCLE: Multi-Turn Query Clarifications with Reinforcement Learning","date":"2023-11-05","arxiv_id":"2311.02737","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-models-implicitly-learn-to","title":"Large language models implicitly learn to straighten neural sentence trajectories to construct a predictive representation of natural language","date":"2023-11-05","arxiv_id":"2311.04930","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-chat-gpt-solve-a-linguistics-exam","title":"Can Chat GPT solve a Linguistics Exam?","date":"2023-11-04","arxiv_id":"2311.02499","repositories_listed":0,"syntology":null},{"url":null,"slug":"understanding-the-natural-language-of-dna","title":"Understanding the Natural Language of DNA using Encoder-Decoder Foundation Models with Byte-level Precision","date":"2023-11-04","arxiv_id":"2311.02333","repositories_listed":0,"syntology":null},{"url":null,"slug":"cosmic-data-efficient-instruction-tuning-for","title":"COSMIC: Data Efficient Instruction-tuning For Speech In-Context Learning","date":"2023-11-03","arxiv_id":"2311.02248","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-free-distillation-of-language-model-by","title":"Data-Free Distillation of Language Model by Text-to-Text Transfer","date":"2023-11-03","arxiv_id":"2311.01689","repositories_listed":0,"syntology":null},{"url":null,"slug":"supermind-ideator-exploring-generative-ai-to","title":"Supermind Ideator: Exploring generative AI to support creative problem-solving","date":"2023-11-03","arxiv_id":"2311.01937","repositories_listed":0,"syntology":null},{"url":null,"slug":"too-much-information-keeping-training-simple","title":"Too Much Information: Keeping Training Simple for BabyLMs","date":"2023-11-03","arxiv_id":"2311.01955","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-study-of-continual-learning-under-language","title":"Continual Learning Under Language Shift","date":"2023-11-02","arxiv_id":"2311.01200","repositories_listed":0,"syntology":null},{"url":null,"slug":"expressive-tts-driven-by-natural-language","title":"Expressive TTS Driven by Natural Language Prompts Using Few Human Annotations","date":"2023-11-02","arxiv_id":"2311.01260","repositories_listed":0,"syntology":null},{"url":null,"slug":"flashdecoding-faster-large-language-model","title":"FlashDecoding++: Faster Large Language Model Inference on GPUs","date":"2023-11-02","arxiv_id":"2311.01282","repositories_listed":0,"syntology":null},{"url":null,"slug":"predicting-question-answering-performance-of","title":"Predicting Question-Answering Performance of Large Language Models through Semantic Consistency","date":"2023-11-02","arxiv_id":"2311.01152","repositories_listed":0,"syntology":null},{"url":null,"slug":"recommendations-by-concise-user-profiles-from","title":"Recommendations by Concise User Profiles from Review Text","date":"2023-11-02","arxiv_id":"2311.01314","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-influence-guided-data-reweighting-for","title":"Self-Influence Guided Data Reweighting for Language Model Pre-training","date":"2023-11-02","arxiv_id":"2311.00913","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-improved-transformer-based-model-for","title":"An Improved Transformer-based Model for Detecting Phishing, Spam, and Ham: A Large Language Model Approach","date":"2023-11-01","arxiv_id":"2311.04913","repositories_listed":0,"syntology":null},{"url":null,"slug":"attention-alignment-and-flexible-positional","title":"Attention Alignment and Flexible Positional Embeddings Improve Transformer Length Extrapolation","date":"2023-11-01","arxiv_id":"2311.00684","repositories_listed":0,"syntology":null},{"url":null,"slug":"clip-ad-a-language-guided-staged-dual-path","title":"CLIP-AD: A Language-Guided Staged Dual-Path Model for Zero-shot Anomaly Detection","date":"2023-11-01","arxiv_id":"2311.00453","repositories_listed":0,"syntology":null},{"url":null,"slug":"form-follows-function-text-to-text","title":"Form follows Function: Text-to-Text Conditional Graph Generation based on Functional Requirements","date":"2023-11-01","arxiv_id":"2311.00444","repositories_listed":0,"syntology":null},{"url":null,"slug":"modeling-subjectivity-by-mimicking-annotator","title":"Modeling subjectivity (by Mimicking Annotator Annotation) in toxic comment identification across diverse communities","date":"2023-11-01","arxiv_id":"2311.00203","repositories_listed":0,"syntology":null},{"url":null,"slug":"zeetad-adapting-pretrained-vision-language","title":"ZEETAD: Adapting Pretrained Vision-Language Model for Zero-Shot End-to-End Temporal Action Detection","date":"2023-11-01","arxiv_id":"2311.00729","repositories_listed":0,"syntology":null},{"url":null,"slug":"bertwich-extending-bert-s-capabilities-to","title":"BERTwich: Extending BERT's Capabilities to Model Dialectal and Noisy Text","date":"2023-10-31","arxiv_id":"2311.00116","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-the-spatial-awareness-capability-of","title":"Enhancing the Spatial Awareness Capability of Multi-Modal Large Language Model","date":"2023-10-31","arxiv_id":"2310.20357","repositories_listed":0,"syntology":null},{"url":null,"slug":"fa-team-at-the-ntcir-17-ufo-task","title":"FA Team at the NTCIR-17 UFO Task","date":"2023-10-31","arxiv_id":"2310.20322","repositories_listed":0,"syntology":null},{"url":null,"slug":"filter-bubbles-and-affective-polarization-in","title":"Filter bubbles and affective polarization in user-personalized large language model outputs","date":"2023-10-31","arxiv_id":"2311.14677","repositories_listed":0,"syntology":null},{"url":null,"slug":"interactive-multi-fidelity-learning-for-cost","title":"Interactive Multi-fidelity Learning for Cost-effective Adaptation of Language Model with Sparse Human Supervision","date":"2023-10-31","arxiv_id":"2310.20153","repositories_listed":0,"syntology":null},{"url":null,"slug":"longer-fixations-more-computation-gaze-guided","title":"Longer Fixations, More Computation: Gaze-Guided Recurrent Neural Networks","date":"2023-10-31","arxiv_id":"2311.00159","repositories_listed":0,"syntology":null},{"url":null,"slug":"vispercep-a-vision-language-approach-to","title":"A Multi-Modal Foundation Model to Assist People with Blindness and Low Vision in Environmental Interaction","date":"2023-10-31","arxiv_id":"2310.20225","repositories_listed":0,"syntology":null},{"url":null,"slug":"adapter-pruning-using-tropical","title":"Adapter Pruning using Tropical Characterization","date":"2023-10-30","arxiv_id":"2310.19232","repositories_listed":0,"syntology":null},{"url":null,"slug":"ehrtutor-enhancing-patient-understanding-of","title":"EHRTutor: Enhancing Patient Understanding of Discharge Instructions","date":"2023-10-30","arxiv_id":"2310.19212","repositories_listed":0,"syntology":null},{"url":null,"slug":"generative-retrieval-augmented-ontologic","title":"Generative retrieval-augmented ontologic graph and multi-agent strategies for interpretive large language model-based materials design","date":"2023-10-30","arxiv_id":"2310.19998","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-input-label-mapping-with","title":"Improving Input-label Mapping with Demonstration Replay for In-context Learning","date":"2023-10-30","arxiv_id":"2310.19572","repositories_listed":0,"syntology":null},{"url":"/paper/integrating-pre-trained-language-model-into","slug":"integrating-pre-trained-language-model-into","title":"Integrating Pre-trained Language Model into Neural Machine Translation","date":"2023-10-30","arxiv_id":"2310.19680","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-language-models-to-detect","title":"Leveraging Language Models to Detect Greenwashing","date":"2023-10-30","arxiv_id":"2311.01469","repositories_listed":0,"syntology":null},{"url":"/paper/moca-measuring-human-language-model-alignment-1","slug":"moca-measuring-human-language-model-alignment-1","title":"MoCa: Measuring Human-Language Model Alignment on Causal and Moral Judgment Tasks","date":"2023-10-30","arxiv_id":"2310.19677","repositories_listed":0,"syntology":{"n":11,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":11,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/moca-measuring-human-language-model-alignment-1#ran","syntology_url":"https://syntology.ai/paper/2310.19677","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.19677"}},"official":null}},{"url":null,"slug":"musical-form-generation","title":"Musical Form Generation","date":"2023-10-30","arxiv_id":"2310.19842","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-impact-of-depth-and-width-on-transformer","title":"The Impact of Depth on Compositional Generalization in Transformer Language Models","date":"2023-10-30","arxiv_id":"2310.19956","repositories_listed":0,"syntology":null},{"url":null,"slug":"robustifying-language-models-with-test-time","title":"Robustifying Language Models with Test-Time Adaptation","date":"2023-10-29","arxiv_id":"2310.19177","repositories_listed":0,"syntology":null},{"url":null,"slug":"teacherlm-teaching-to-fish-rather-than-giving","title":"TeacherLM: Teaching to Fish Rather Than Giving the Fish, Language Modeling Likewise","date":"2023-10-29","arxiv_id":"2310.19019","repositories_listed":0,"syntology":null},{"url":null,"slug":"reboost-large-language-model-based-text-to","title":"Reboost Large Language Model-based Text-to-SQL, Text-to-Python, and Text-to-Function -- with Real Applications in Traffic Domain","date":"2023-10-28","arxiv_id":"2310.18752","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-nl-to-cypher-translation-for-kbqa","title":"Robust NL-to-Cypher Translation for KBQA: Harnessing Large Language Model with Chain of Prompts","date":"2023-10-28","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"generative-ai-for-software-metadata-overview","title":"Generative AI for Software Metadata: Overview of the Information Retrieval in Software Engineering Track at FIRE 2023","date":"2023-10-27","arxiv_id":"2311.03374","repositories_listed":0,"syntology":null},{"url":null,"slug":"interactive-robot-learning-from-verbal","title":"Interactive Robot Learning from Verbal Correction","date":"2023-10-26","arxiv_id":"2310.17555","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-models-as-generalizable","title":"Large Language Models as Generalizable Policies for Embodied Tasks","date":"2023-10-26","arxiv_id":"2310.17722","repositories_listed":0,"syntology":null},{"url":null,"slug":"boost-harnessing-black-box-control-to-boost","title":"BOOST: Harnessing Black-Box Control to Boost Commonsense in LMs' Generation","date":"2023-10-25","arxiv_id":"2310.17054","repositories_listed":0,"syntology":null},{"url":null,"slug":"controlled-decoding-from-language-models","title":"Controlled Decoding from Language Models","date":"2023-10-25","arxiv_id":"2310.17022","repositories_listed":0,"syntology":null},{"url":null,"slug":"faithful-path-language-modelling-for","title":"Faithful Path Language Modeling for Explainable Recommendation over Knowledge Graph","date":"2023-10-25","arxiv_id":"2310.16452","repositories_listed":0,"syntology":null},{"url":null,"slug":"fedtherapist-mental-health-monitoring-with","title":"FedTherapist: Mental Health Monitoring with User-Generated Linguistic Expressions on Smartphones via Federated Learning","date":"2023-10-25","arxiv_id":"2310.16538","repositories_listed":0,"syntology":null},{"url":null,"slug":"general-point-model-with-autoencoding-and","title":"General Point Model with Autoencoding and Autoregressive","date":"2023-10-25","arxiv_id":"2310.16861","repositories_listed":0,"syntology":null},{"url":null,"slug":"math-pvs-a-large-language-model-framework-to","title":"math-PVS: A Large Language Model Framework to Map Scientific Publications to PVS Theories","date":"2023-10-25","arxiv_id":"2310.17064","repositories_listed":0,"syntology":null},{"url":null,"slug":"multiple-key-value-strategy-in-recommendation","title":"Multiple Key-value Strategy in Recommendation Systems Incorporating Large Language Model","date":"2023-10-25","arxiv_id":"2310.16409","repositories_listed":0,"syntology":null},{"url":null,"slug":"rcagent-cloud-root-cause-analysis-by","title":"RCAgent: Cloud Root Cause Analysis by Autonomous Agents with Tool-Augmented Large Language Models","date":"2023-10-25","arxiv_id":"2310.16340","repositories_listed":0,"syntology":null},{"url":null,"slug":"subspace-chronicles-how-linguistic","title":"Subspace Chronicles: How Linguistic Information Emerges, Shifts and Interacts during Language Model Training","date":"2023-10-25","arxiv_id":"2310.16484","repositories_listed":0,"syntology":null},{"url":null,"slug":"transformer-based-live-update-generation-for","title":"Transformer-based Live Update Generation for Soccer Matches from Microblog Posts","date":"2023-10-25","arxiv_id":"2310.16368","repositories_listed":0,"syntology":null},{"url":null,"slug":"url-bert-training-webpage-representations-via","title":"URL-BERT: Training Webpage Representations via Social Media Engagements","date":"2023-10-25","arxiv_id":"2310.16303","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-language-model-with-limited-memory-capacity","title":"A Language Model with Limited Memory Capacity Captures Interference in Human Sentence Processing","date":"2023-10-24","arxiv_id":"2310.16142","repositories_listed":0,"syntology":null},{"url":null,"slug":"blp-2023-task-2-sentiment-analysis","title":"BLP-2023 Task 2: Sentiment Analysis","date":"2023-10-24","arxiv_id":"2310.16183","repositories_listed":0,"syntology":null},{"url":null,"slug":"desiq-towards-an-unbiased-challenging","title":"DeSIQ: Towards an Unbiased, Challenging Benchmark for Social Intelligence Understanding","date":"2023-10-24","arxiv_id":"2310.18359","repositories_listed":0,"syntology":null},{"url":null,"slug":"e-sparse-boosting-the-large-language-model","title":"E-Sparse: Boosting the Large Language Model Inference through Entropy-based N:M Sparsity","date":"2023-10-24","arxiv_id":"2310.15929","repositories_listed":0,"syntology":null},{"url":null,"slug":"facilitating-self-guided-mental-health","title":"Facilitating Self-Guided Mental Health Interventions Through Human-Language Model Interaction: A Case Study of Cognitive Restructuring","date":"2023-10-24","arxiv_id":"2310.15461","repositories_listed":0,"syntology":null},{"url":null,"slug":"fltrojan-privacy-leakage-attacks-against","title":"FLTrojan: Privacy Leakage Attacks against Federated Language Models Through Selective Weight Tampering","date":"2023-10-24","arxiv_id":"2310.16152","repositories_listed":0,"syntology":null},{"url":null,"slug":"mindllm-pre-training-lightweight-large","title":"MindLLM: Pre-training Lightweight Large Language Model from Scratch, Evaluations and Domain Applications","date":"2023-10-24","arxiv_id":"2310.15777","repositories_listed":0,"syntology":null},{"url":null,"slug":"prevalence-and-prevention-of-large-language","title":"Prevalence and prevention of large language model use in crowd work","date":"2023-10-24","arxiv_id":"2310.15683","repositories_listed":0,"syntology":null},{"url":null,"slug":"promptinfuser-how-tightly-coupling-ai-and-ui","title":"PromptInfuser: How Tightly Coupling AI and UI Design Impacts Designers' Workflows","date":"2023-10-24","arxiv_id":"2310.15435","repositories_listed":0,"syntology":null},{"url":null,"slug":"retrieval-based-knowledge-transfer-an","title":"Retrieval-based Knowledge Transfer: An Effective Approach for Extreme Large Language Model Compression","date":"2023-10-24","arxiv_id":"2310.15594","repositories_listed":0,"syntology":null},{"url":null,"slug":"rosetta-stone-at-ksaa-rd-shared-task-a-hop","title":"Rosetta Stone at KSAA-RD Shared Task: A Hop From Language Modeling To Word--Definition Alignment","date":"2023-10-24","arxiv_id":"2310.15823","repositories_listed":0,"syntology":null},{"url":null,"slug":"tcra-llm-token-compression-retrieval","title":"TCRA-LLM: Token Compression Retrieval Augmented Large Language Model for Inference Cost Reduction","date":"2023-10-24","arxiv_id":"2310.15556","repositories_listed":0,"syntology":null},{"url":null,"slug":"unnatural-language-processing-how-do-language","title":"Unnatural language processing: How do language models handle machine-generated prompts?","date":"2023-10-24","arxiv_id":"2310.15829","repositories_listed":0,"syntology":null},{"url":null,"slug":"webwise-web-interface-control-and-sequential","title":"WebWISE: Web Interface Control and Sequential Exploration with Large Language Models","date":"2023-10-24","arxiv_id":"2310.16042","repositories_listed":0,"syntology":null},{"url":null,"slug":"branch-solve-merge-improves-large-language","title":"Branch-Solve-Merge Improves Large Language Model Evaluation and Generation","date":"2023-10-23","arxiv_id":"2310.15123","repositories_listed":0,"syntology":null},{"url":null,"slug":"counting-the-bugs-in-chatgpt-s-wugs-a","title":"Counting the Bugs in ChatGPT's Wugs: A Multilingual Investigation into the Morphological Capabilities of a Large Language Model","date":"2023-10-23","arxiv_id":"2310.15113","repositories_listed":0,"syntology":null},{"url":null,"slug":"generative-pre-trained-transformer-for-1","title":"Generative Pre-trained Transformer for Vietnamese Community-based COVID-19 Question Answering","date":"2023-10-23","arxiv_id":"2310.14602","repositories_listed":0,"syntology":null},{"url":null,"slug":"health-disparities-through-generative-ai","title":"Health Disparities through Generative AI Models: A Comparison Study Using A Domain Specific large language model","date":"2023-10-23","arxiv_id":"2310.18355","repositories_listed":0,"syntology":null},{"url":null,"slug":"irreducible-curriculum-for-language-model","title":"Irreducible Curriculum for Language Model Pretraining","date":"2023-10-23","arxiv_id":"2310.15389","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-search-model-redefining-search-stack-in","title":"Large Search Model: Redefining Search Stack in the Era of LLMs","date":"2023-10-23","arxiv_id":"2310.14587","repositories_listed":0,"syntology":null},{"url":null,"slug":"understanding-the-inner-workings-of-language","title":"Understanding the Inner Workings of Language Models Through Representation Dissimilarity","date":"2023-10-23","arxiv_id":"2310.14993","repositories_listed":0,"syntology":null},{"url":null,"slug":"why-llms-hallucinate-and-how-to-get","title":"Why LLMs Hallucinate, and How to Get (Evidential) Closure: Perceptual, Intensional, and Extensional Learning for Faithful Natural Language Generation","date":"2023-10-23","arxiv_id":"2310.15355","repositories_listed":0,"syntology":null},{"url":null,"slug":"boosting-unsupervised-machine-translation","title":"Boosting Unsupervised Machine Translation with Pseudo-Parallel Data","date":"2023-10-22","arxiv_id":"2310.14262","repositories_listed":0,"syntology":null},{"url":null,"slug":"customising-general-large-language-models-for","title":"Customising General Large Language Models for Specialised Emotion Recognition Tasks","date":"2023-10-22","arxiv_id":"2310.14225","repositories_listed":0,"syntology":null},{"url":null,"slug":"one-model-for-all-large-language-models-are","title":"One Model for All: Large Language Models are Domain-Agnostic Recommendation Systems","date":"2023-10-22","arxiv_id":"2310.14304","repositories_listed":0,"syntology":null},{"url":null,"slug":"which-prompts-make-the-difference-data","title":"Which Prompts Make The Difference? Data Prioritization For Efficient Human LLM Evaluation","date":"2023-10-22","arxiv_id":"2310.14424","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-reward-for-physical-skills-using","title":"Learning Reward for Physical Skills using Large Language Model","date":"2023-10-21","arxiv_id":"2310.14092","repositories_listed":0,"syntology":null},{"url":"/paper/medeval-a-multi-level-multi-task-and-multi","slug":"medeval-a-multi-level-multi-task-and-multi","title":"MedEval: A Multi-Level, Multi-Task, and Multi-Domain Medical Benchmark for Language Model Evaluation","date":"2023-10-21","arxiv_id":"2310.14088","repositories_listed":0,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":7,"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) · 3 unverified","sample_list":"/paper/medeval-a-multi-level-multi-task-and-multi#ran","syntology_url":"https://syntology.ai/paper/2310.14088","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.14088"}},"official":null}},{"url":null,"slug":"sentiment-analysis-across-multiple-african","title":"Sentiment Analysis Across Multiple African Languages: A Current Benchmark","date":"2023-10-21","arxiv_id":"2310.14120","repositories_listed":0,"syntology":null},{"url":null,"slug":"ask-language-model-to-clean-your-noisy","title":"Ask Language Model to Clean Your Noisy Translation Data","date":"2023-10-20","arxiv_id":"2310.13469","repositories_listed":0,"syntology":null},{"url":null,"slug":"cache-distil-optimising-api-calls-to-large","title":"Cache & Distil: Optimising API Calls to Large Language Models","date":"2023-10-20","arxiv_id":"2310.13561","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-zero-shot-crypto-sentiment-with","title":"Enhancing Zero-Shot Crypto Sentiment with Fine-tuned Language Model and Prompt Engineering","date":"2023-10-20","arxiv_id":"2310.13226","repositories_listed":0,"syntology":null},{"url":null,"slug":"gendistiller-distilling-pre-trained-language","title":"GenDistiller: Distilling Pre-trained Language Models based on Generative Models","date":"2023-10-20","arxiv_id":"2310.13418","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-past-present-and-future-of-typological","title":"The Past, Present, and Future of Typological Databases in NLP","date":"2023-10-20","arxiv_id":"2310.13440","repositories_listed":0,"syntology":null},{"url":null,"slug":"thoroughly-modeling-multi-domain-pre-trained","title":"Thoroughly Modeling Multi-domain Pre-trained Recommendation as Language","date":"2023-10-20","arxiv_id":"2310.13540","repositories_listed":0,"syntology":null},{"url":null,"slug":"wordart-designer-user-driven-artistic","title":"WordArt Designer: User-Driven Artistic Typography Synthesis using Large Language Models","date":"2023-10-20","arxiv_id":"2310.18332","repositories_listed":0,"syntology":null},{"url":null,"slug":"zero-shot-sharpness-aware-quantization-for","title":"Zero-Shot Sharpness-Aware Quantization for Pre-trained Language Models","date":"2023-10-20","arxiv_id":"2310.13315","repositories_listed":0,"syntology":null}],"record_sha256":"a06cc15dca161b4b1f7d64de3509c6337889ca3d570003f733c6f7c41d9d2353","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}