{"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/122","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":122,"pages_in_order":177,"rows_per_page":100,"rows":[12101,12200],"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/121","next":"/task/language-modelling/papers/123","papers":[{"url":null,"slug":"legend-at-araieval-shared-task-persuasion","title":"Legend at ArAIEval Shared Task: Persuasion Technique Detection using a Language-Agnostic Text Representation Model","date":"2023-10-14","arxiv_id":"2310.09661","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-generative-ai-improving-software","title":"Leveraging Generative AI: Improving Software Metadata Classification with Generated Code-Comment Pairs","date":"2023-10-14","arxiv_id":"2311.03365","repositories_listed":0,"syntology":null},{"url":null,"slug":"software-metadata-classification-based-on","title":"Software Metadata Classification based on Generative Artificial Intelligence","date":"2023-10-14","arxiv_id":"2310.13006","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-case-based-persistent-memory-for-a-large","title":"A Case-Based Persistent Memory for a Large Language Model","date":"2023-10-13","arxiv_id":"2310.08842","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-ml-llm-pairing-for-better-code-comment","title":"A ML-LLM pairing for better code comment classification","date":"2023-10-13","arxiv_id":"2310.10275","repositories_listed":0,"syntology":null},{"url":null,"slug":"agentcf-collaborative-learning-with","title":"AgentCF: Collaborative Learning with Autonomous Language Agents for Recommender Systems","date":"2023-10-13","arxiv_id":"2310.09233","repositories_listed":0,"syntology":null},{"url":null,"slug":"clickprompt-ctr-models-are-strong-prompt","title":"ClickPrompt: CTR Models are Strong Prompt Generators for Adapting Language Models to CTR Prediction","date":"2023-10-13","arxiv_id":"2310.09234","repositories_listed":0,"syntology":null},{"url":null,"slug":"collaborative-contextualization-bridging-the","title":"Collaborative Semantic Alignment in Recommendation Systems","date":"2023-10-13","arxiv_id":"2310.09400","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-bert-based-visual-question","title":"Enhancing BERT-Based Visual Question Answering through Keyword-Driven Sentence Selection","date":"2023-10-13","arxiv_id":"2310.09432","repositories_listed":0,"syntology":null},{"url":null,"slug":"incremental-object-detection-with-clip","title":"Incremental Object Detection with CLIP","date":"2023-10-13","arxiv_id":"2310.08815","repositories_listed":0,"syntology":null},{"url":null,"slug":"interactive-navigation-in-environments-with","title":"Interactive Navigation in Environments with Traversable Obstacles Using Large Language and Vision-Language Models","date":"2023-10-13","arxiv_id":"2310.08873","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-consensus-game-language-model-generation","title":"The Consensus Game: Language Model Generation via Equilibrium Search","date":"2023-10-13","arxiv_id":"2310.09139","repositories_listed":0,"syntology":null},{"url":null,"slug":"distillspec-improving-speculative-decoding","title":"DistillSpec: Improving Speculative Decoding via Knowledge Distillation","date":"2023-10-12","arxiv_id":"2310.08461","repositories_listed":0,"syntology":null},{"url":null,"slug":"harnessing-large-language-models-empathetic","title":"Harnessing Large Language Models' Empathetic Response Generation Capabilities for Online Mental Health Counselling Support","date":"2023-10-12","arxiv_id":"2310.08017","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-models-can-replicate-cross","title":"Large language models can replicate cross-cultural differences in personality","date":"2023-10-12","arxiv_id":"2310.10679","repositories_listed":0,"syntology":null},{"url":null,"slug":"multimodal-large-language-model-for-visual","title":"Multimodal Large Language Model for Visual Navigation","date":"2023-10-12","arxiv_id":"2310.08669","repositories_listed":0,"syntology":null},{"url":null,"slug":"promptor-a-conversational-and-autonomous","title":"Promptor: A Conversational and Autonomous Prompt Generation Agent for Intelligent Text Entry Techniques","date":"2023-10-12","arxiv_id":"2310.08101","repositories_listed":0,"syntology":null},{"url":null,"slug":"toward-joint-language-modeling-for-speech","title":"Toward Joint Language Modeling for Speech Units and Text","date":"2023-10-12","arxiv_id":"2310.08715","repositories_listed":0,"syntology":null},{"url":null,"slug":"ziya-vl-bilingual-large-vision-language-model","title":"Ziya-Visual: Bilingual Large Vision-Language Model via Multi-Task Instruction Tuning","date":"2023-10-12","arxiv_id":"2310.08166","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comparative-study-of-pre-trained-cnns-and","title":"A Comparative Study of Pre-trained CNNs and GRU-Based Attention for Image Caption Generation","date":"2023-10-11","arxiv_id":"2310.07252","repositories_listed":0,"syntology":null},{"url":null,"slug":"clausewitzgpt-framework-a-new-frontier-in","title":"ClausewitzGPT Framework: A New Frontier in Theoretical Large Language Model Enhanced Information Operations","date":"2023-10-11","arxiv_id":"2310.07099","repositories_listed":0,"syntology":null},{"url":null,"slug":"crosslingual-structural-priming-and-the-pre","title":"Crosslingual Structural Priming and the Pre-Training Dynamics of Bilingual Language Models","date":"2023-10-11","arxiv_id":"2310.07929","repositories_listed":0,"syntology":null},{"url":null,"slug":"fast-electra-for-efficient-pre-training","title":"Fast-ELECTRA for Efficient Pre-training","date":"2023-10-11","arxiv_id":"2310.07347","repositories_listed":0,"syntology":null},{"url":null,"slug":"langnav-language-as-a-perceptual","title":"LangNav: Language as a Perceptual Representation for Navigation","date":"2023-10-11","arxiv_id":"2310.07889","repositories_listed":0,"syntology":null},{"url":null,"slug":"matchat-a-large-language-model-and","title":"MatChat: A Large Language Model and Application Service Platform for Materials Science","date":"2023-10-11","arxiv_id":"2310.07197","repositories_listed":0,"syntology":null},{"url":null,"slug":"measuring-feature-sparsity-in-language-models","title":"Measuring Feature Sparsity in Language Models","date":"2023-10-11","arxiv_id":"2310.07837","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-foundation-models-for-learning-on","title":"From Supervised to Generative: A Novel Paradigm for Tabular Deep Learning with Large Language Models","date":"2023-10-11","arxiv_id":"2310.07338","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-multi-facet-paradigm-to-bridge-large","title":"Bridging Items and Language: A Transition Paradigm for Large Language Model-Based Recommendation","date":"2023-10-10","arxiv_id":"2310.06491","repositories_listed":0,"syntology":null},{"url":null,"slug":"acoustic-model-fusion-for-end-to-end-speech","title":"Acoustic Model Fusion for End-to-end Speech Recognition","date":"2023-10-10","arxiv_id":"2310.07062","repositories_listed":0,"syntology":null},{"url":null,"slug":"answer-candidate-type-selection-text-to-text","title":"Answer Candidate Type Selection: Text-to-Text Language Model for Closed Book Question Answering Meets Knowledge Graphs","date":"2023-10-10","arxiv_id":"2310.07008","repositories_listed":0,"syntology":null},{"url":null,"slug":"autoad-ii-the-sequel-who-when-and-what-in-1","title":"AutoAD II: The Sequel -- Who, When, and What in Movie Audio Description","date":"2023-10-10","arxiv_id":"2310.06838","repositories_listed":0,"syntology":null},{"url":null,"slug":"bc4llm-trusted-artificial-intelligence-when","title":"BC4LLM: Trusted Artificial Intelligence When Blockchain Meets Large Language Models","date":"2023-10-10","arxiv_id":"2310.06278","repositories_listed":0,"syntology":null},{"url":null,"slug":"codefuse-13b-a-pretrained-multi-lingual-code","title":"CodeFuse-13B: A Pretrained Multi-lingual Code Large Language Model","date":"2023-10-10","arxiv_id":"2310.06266","repositories_listed":0,"syntology":null},{"url":null,"slug":"dobby-a-conversational-service-robot-driven","title":"Dobby: A Conversational Service Robot Driven by GPT-4","date":"2023-10-10","arxiv_id":"2310.06303","repositories_listed":0,"syntology":null},{"url":null,"slug":"generating-and-evaluating-tests-for-k-12","title":"Generating and Evaluating Tests for K-12 Students with Language Model Simulations: A Case Study on Sentence Reading Efficiency","date":"2023-10-10","arxiv_id":"2310.06837","repositories_listed":0,"syntology":null},{"url":null,"slug":"get-the-gist-using-large-language-models-for","title":"Get the gist? Using large language models for few-shot decontextualization","date":"2023-10-10","arxiv_id":"2310.06254","repositories_listed":0,"syntology":null},{"url":null,"slug":"jailbreak-and-guard-aligned-language-models","title":"Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations","date":"2023-10-10","arxiv_id":"2310.06387","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-meta-learning-perspective-on-transformers","title":"A Meta-Learning Perspective on Transformers for Causal Language Modeling","date":"2023-10-09","arxiv_id":"2310.05884","repositories_listed":0,"syntology":null},{"url":null,"slug":"ccae-a-corpus-of-chinese-based-asian","title":"CCAE: A Corpus of Chinese-based Asian Englishes","date":"2023-10-09","arxiv_id":"2310.05381","repositories_listed":0,"syntology":null},{"url":null,"slug":"estimating-numbers-without-regression","title":"Estimating Numbers without Regression","date":"2023-10-09","arxiv_id":"2310.06204","repositories_listed":0,"syntology":null},{"url":null,"slug":"explaining-the-complex-task-reasoning-of","title":"Parrot Mind: Towards Explaining the Complex Task Reasoning of Pretrained Large Language Models with Template-Content Structure","date":"2023-10-09","arxiv_id":"2310.05452","repositories_listed":0,"syntology":null},{"url":null,"slug":"factual-and-personalized-recommendations","title":"Factual and Personalized Recommendations using Language Models and Reinforcement Learning","date":"2023-10-09","arxiv_id":"2310.06176","repositories_listed":0,"syntology":null},{"url":null,"slug":"guiding-language-model-reasoning-with","title":"Guiding Language Model Reasoning with Planning Tokens","date":"2023-10-09","arxiv_id":"2310.05707","repositories_listed":0,"syntology":null},{"url":"/paper/mbbc-exploring-the-multilingual-maze","slug":"mbbc-exploring-the-multilingual-maze","title":"Exploring the Maze of Multilingual Modeling","date":"2023-10-09","arxiv_id":"2310.05404","repositories_listed":0,"syntology":null},{"url":null,"slug":"rethinking-memory-and-communication-cost-for","title":"Rethinking Memory and Communication Cost for Efficient Large Language Model Training","date":"2023-10-09","arxiv_id":"2310.06003","repositories_listed":0,"syntology":null},{"url":null,"slug":"scaling-studies-for-efficient-parameter","title":"Scaling Studies for Efficient Parameter Search and Parallelism for Large Language Model Pre-training","date":"2023-10-09","arxiv_id":"2310.05350","repositories_listed":0,"syntology":null},{"url":null,"slug":"terminology-aware-translation-with","title":"Terminology-Aware Translation with Constrained Decoding and Large Language Model Prompting","date":"2023-10-09","arxiv_id":"2310.05824","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-importance-of-prompt-tuning-for-automated","title":"The Importance of Prompt Tuning for Automated Neuron Explanations","date":"2023-10-09","arxiv_id":"2310.06200","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-potential-of-large-language-models-for","title":"The potential of large language models for improving probability learning: A study on ChatGPT3.5 and first-year computer engineering students","date":"2023-10-09","arxiv_id":"2310.05686","repositories_listed":0,"syntology":null},{"url":null,"slug":"transformers-and-large-language-models-for","title":"Transformers and Large Language Models for Chemistry and Drug Discovery","date":"2023-10-09","arxiv_id":"2310.06083","repositories_listed":0,"syntology":null},{"url":null,"slug":"breaking-down-word-semantics-from-pre-trained","title":"Breaking Down Word Semantics from Pre-trained Language Models through Layer-wise Dimension Selection","date":"2023-10-08","arxiv_id":"2310.05115","repositories_listed":0,"syntology":null},{"url":null,"slug":"chatradio-valuer-a-chat-large-language-model","title":"ChatRadio-Valuer: A Chat Large Language Model for Generalizable Radiology Report Generation Based on Multi-institution and Multi-system Data","date":"2023-10-08","arxiv_id":"2310.05242","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-the-usage-of-chinese-pinyin-in","title":"Exploring the Usage of Chinese Pinyin in Pretraining","date":"2023-10-08","arxiv_id":"2310.04960","repositories_listed":0,"syntology":null},{"url":null,"slug":"generative-spoken-language-model-based-on","title":"Generative Spoken Language Model based on continuous word-sized audio tokens","date":"2023-10-08","arxiv_id":"2310.05224","repositories_listed":0,"syntology":null},{"url":null,"slug":"loose-lips-sink-ships-mitigating-length-bias","title":"Loose lips sink ships: Mitigating Length Bias in Reinforcement Learning from Human Feedback","date":"2023-10-08","arxiv_id":"2310.05199","repositories_listed":0,"syntology":null},{"url":null,"slug":"measuring-reasoning-capabilities-of-chatgpt","title":"Measuring reasoning capabilities of ChatGPT","date":"2023-10-08","arxiv_id":"2310.05993","repositories_listed":0,"syntology":null},{"url":null,"slug":"mindfuldiary-harnessing-large-language-model","title":"MindfulDiary: Harnessing Large Language Model to Support Psychiatric Patients' Journaling","date":"2023-10-08","arxiv_id":"2310.05231","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimizing-large-language-models-to-expedite","title":"Optimizing Large Language Models to Expedite the Development of Smart Contracts","date":"2023-10-08","arxiv_id":"2310.05178","repositories_listed":0,"syntology":null},{"url":null,"slug":"synslator-an-interactive-machine-translation","title":"Synslator: An Interactive Machine Translation Tool with Online Learning","date":"2023-10-08","arxiv_id":"2310.05025","repositories_listed":0,"syntology":null},{"url":null,"slug":"iluvui-instruction-tuned-language-vision","title":"ILuvUI: Instruction-tuned LangUage-Vision modeling of UIs from Machine Conversations","date":"2023-10-07","arxiv_id":"2310.04869","repositories_listed":0,"syntology":null},{"url":null,"slug":"prompt-to-os-p2os-revolutionizing-operating","title":"Prompt-to-OS (P2OS): Revolutionizing Operating Systems and Human-Computer Interaction with Integrated AI Generative Models","date":"2023-10-07","arxiv_id":"2310.04875","repositories_listed":0,"syntology":null},{"url":null,"slug":"question-focused-summarization-by-decomposing","title":"Question-focused Summarization by Decomposing Articles into Facts and Opinions and Retrieving Entities","date":"2023-10-07","arxiv_id":"2310.04880","repositories_listed":0,"syntology":null},{"url":null,"slug":"tree-gpt-modular-large-language-model-expert","title":"Tree-GPT: Modular Large Language Model Expert System for Forest Remote Sensing Image Understanding and Interactive Analysis","date":"2023-10-07","arxiv_id":"2310.04698","repositories_listed":0,"syntology":null},{"url":null,"slug":"brainscuba-fine-grained-natural-language","title":"BrainSCUBA: Fine-Grained Natural Language Captions of Visual Cortex Selectivity","date":"2023-10-06","arxiv_id":"2310.04420","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-task-structures-to-world-models-what-do","title":"From task structures to world models: What do LLMs know?","date":"2023-10-06","arxiv_id":"2310.04276","repositories_listed":0,"syntology":null},{"url":null,"slug":"functional-interpolation-for-relative","title":"Functional Interpolation for Relative Positions Improves Long Context Transformers","date":"2023-10-06","arxiv_id":"2310.04418","repositories_listed":0,"syntology":null},{"url":null,"slug":"keyword-augmented-retrieval-novel-framework","title":"Keyword Augmented Retrieval: Novel framework for Information Retrieval integrated with speech interface","date":"2023-10-06","arxiv_id":"2310.04205","repositories_listed":0,"syntology":null},{"url":null,"slug":"lending-interaction-wings-to-recommender","title":"Lending Interaction Wings to Recommender Systems with Conversational Agents","date":"2023-10-06","arxiv_id":"2310.04230","repositories_listed":0,"syntology":null},{"url":null,"slug":"quantized-transformer-language-model","title":"Quantized Transformer Language Model Implementations on Edge Devices","date":"2023-10-06","arxiv_id":"2310.03971","repositories_listed":0,"syntology":null},{"url":null,"slug":"understanding-prompt-engineering-may-not","title":"Understanding prompt engineering may not require rethinking generalization","date":"2023-10-06","arxiv_id":"2310.03957","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-5-utr-language-model-for-decoding","title":"A 5' UTR Language Model for Decoding Untranslated Regions of mRNA and Function Predictions","date":"2023-10-05","arxiv_id":"2310.03281","repositories_listed":0,"syntology":null},{"url":null,"slug":"controllable-multi-document-summarization","title":"Controllable Multi-document Summarization: Coverage & Coherence Intuitive Policy with Large Language Model Based Rewards","date":"2023-10-05","arxiv_id":"2310.03473","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-representations-of-first-person-pronouns","title":"Deep Representations of First-person Pronouns for Prediction of Depression Symptom Severity","date":"2023-10-05","arxiv_id":"2310.03232","repositories_listed":0,"syntology":null},{"url":null,"slug":"llm-based-multi-document-summarization","title":"LLM Based Multi-Document Summarization Exploiting Main-Event Biased Monotone Submodular Content Extraction","date":"2023-10-05","arxiv_id":"2310.03414","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-language-model-pruning-for-automatic","title":"Neural Language Model Pruning for Automatic Speech Recognition","date":"2023-10-05","arxiv_id":"2310.03424","repositories_listed":0,"syntology":null},{"url":null,"slug":"dual-prompt-tuning-for-domain-aware-federated","title":"Learning to Prompt Your Domain for Vision-Language Models","date":"2023-10-04","arxiv_id":"2310.03103","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-words-to-watts-benchmarking-the-energy","title":"From Words to Watts: Benchmarking the Energy Costs of Large Language Model Inference","date":"2023-10-04","arxiv_id":"2310.03003","repositories_listed":0,"syntology":null},{"url":null,"slug":"heterogeneous-federated-learning-using","title":"Heterogeneous Federated Learning Using Knowledge Codistillation","date":"2023-10-04","arxiv_id":"2310.02549","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-and-interpretable-medical-image","title":"Robust and Interpretable Medical Image Classifiers via Concept Bottleneck Models","date":"2023-10-04","arxiv_id":"2310.03182","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-evolutionary-model-of-personality-traits","title":"An evolutionary model of personality traits related to cooperative behavior using a large language model","date":"2023-10-03","arxiv_id":"2310.05976","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-a-student-large-language-model-perform-as","title":"Can a student Large Language Model perform as well as it's teacher?","date":"2023-10-03","arxiv_id":"2310.02421","repositories_listed":0,"syntology":null},{"url":null,"slug":"hpc-gpt-integrating-large-language-model-for","title":"HPC-GPT: Integrating Large Language Model for High-Performance Computing","date":"2023-10-03","arxiv_id":"2311.12833","repositories_listed":0,"syntology":null},{"url":null,"slug":"nugget-2d-dynamic-contextual-compression-for","title":"Dodo: Dynamic Contextual Compression for Decoder-only LMs","date":"2023-10-03","arxiv_id":"2310.02409","repositories_listed":0,"syntology":null},{"url":null,"slug":"tuning-large-language-model-for-end-to-end","title":"Tuning Large language model for End-to-end Speech Translation","date":"2023-10-03","arxiv_id":"2310.02050","repositories_listed":0,"syntology":null},{"url":null,"slug":"twiz-the-wizard-of-multimodal-conversational","title":"TWIZ-v2: The Wizard of Multimodal Conversational-Stimulus","date":"2023-10-03","arxiv_id":"2310.02118","repositories_listed":0,"syntology":null},{"url":null,"slug":"who-s-harry-potter-approximate-unlearning-in","title":"Who's Harry Potter? Approximate Unlearning in LLMs","date":"2023-10-03","arxiv_id":"2310.02238","repositories_listed":0,"syntology":null},{"url":null,"slug":"drivegpt4-interpretable-end-to-end-autonomous","title":"DriveGPT4: Interpretable End-to-end Autonomous Driving via Large Language Model","date":"2023-10-02","arxiv_id":"2310.01412","repositories_listed":0,"syntology":null},{"url":null,"slug":"error-norm-truncation-robust-training-in-the","title":"Error Norm Truncation: Robust Training in the Presence of Data Noise for Text Generation Models","date":"2023-10-02","arxiv_id":"2310.00840","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-emotional-expression-and-cohesion","title":"Improving Emotional Expression and Cohesion in Image-Based Playlist Description and Music Topics: A Continuous Parameterization Approach","date":"2023-10-02","arxiv_id":"2310.01248","repositories_listed":0,"syntology":null},{"url":null,"slug":"language-model-decoding-as-direct-metrics","title":"Language Model Decoding as Direct Metrics Optimization","date":"2023-10-02","arxiv_id":"2310.01041","repositories_listed":0,"syntology":null},{"url":null,"slug":"loft-local-proxy-fine-tuning-for-improving","title":"LoFT: Local Proxy Fine-tuning For Improving Transferability Of Adversarial Attacks Against Large Language Model","date":"2023-10-02","arxiv_id":"2310.04445","repositories_listed":0,"syntology":null},{"url":null,"slug":"melody-conditioned-lyrics-generation-via-fine","title":"Syllable-level lyrics generation from melody exploiting character-level language model","date":"2023-10-02","arxiv_id":"2310.00863","repositories_listed":0,"syntology":null},{"url":null,"slug":"polysketchformer-fast-transformers-via","title":"PolySketchFormer: Fast Transformers via Sketching Polynomial Kernels","date":"2023-10-02","arxiv_id":"2310.01655","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-logiglue-a-brief-survey-and-a","title":"Towards LogiGLUE: A Brief Survey and A Benchmark for Analyzing Logical Reasoning Capabilities of Language Models","date":"2023-10-02","arxiv_id":"2310.00836","repositories_listed":0,"syntology":null},{"url":null,"slug":"comics-for-everyone-generating-accessible","title":"Comics for Everyone: Generating Accessible Text Descriptions for Comic Strips","date":"2023-10-01","arxiv_id":"2310.00698","repositories_listed":0,"syntology":null},{"url":null,"slug":"faithful-explanations-of-black-box-nlp-models","title":"Faithful Explanations of Black-box NLP Models Using LLM-generated Counterfactuals","date":"2023-10-01","arxiv_id":"2310.00603","repositories_listed":0,"syntology":null},{"url":null,"slug":"meta-semantic-template-for-evaluation-of","title":"Meta Semantic Template for Evaluation of Large Language Models","date":"2023-10-01","arxiv_id":"2310.01448","repositories_listed":0,"syntology":null},{"url":null,"slug":"parameter-efficient-tuning-helps-language","title":"Parameter-Efficient Tuning Helps Language Model Alignment","date":"2023-10-01","arxiv_id":"2310.00819","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-language-driven-self-evolution-for-large","title":"SELF: Self-Evolution with Language Feedback","date":"2023-10-01","arxiv_id":"2310.00533","repositories_listed":0,"syntology":null},{"url":null,"slug":"wasa-watermark-based-source-attribution-for","title":"Source Attribution for Large Language Model-Generated Data","date":"2023-10-01","arxiv_id":"2310.00646","repositories_listed":0,"syntology":null}],"record_sha256":"7e49cff7064b0c06c772c7539ad646e1fdb2f2cf2cf28f4507373e050e002a04","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}