{"list":"other","total":88,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2310.06825","title":"Mistral 7B","created":"2023-10-10","cited_by_count":3164},{"id":"2211.05100","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","created":"2022-11-09","cited_by_count":1984},{"id":"2404.14219","title":"Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone","created":"2024-04-22","cited_by_count":1917},{"id":"2010.11934","title":"mT5: A massively multilingual pre-trained text-to-text transformer","created":"2020-10-22","cited_by_count":1818},{"id":"2310.01405","title":"Representation Engineering: A Top-Down Approach to AI Transparency","created":"2023-10-02","cited_by_count":1336},{"id":"2306.03341","title":"Inference-Time Intervention: Eliciting Truthful Answers from a Language Model","created":"2023-06-06","cited_by_count":1302},{"id":"2305.11206","title":"LIMA: Less Is More for Alignment","created":"2023-05-18","cited_by_count":1100},{"id":"1901.07291","title":"Cross-lingual Language Model Pretraining","created":"2019-01-22","cited_by_count":1090},{"id":"2311.03658","title":"The Linear Representation Hypothesis and the Geometry of Large Language Models","created":"2023-11-07","cited_by_count":716},{"id":"1906.01502","title":"How multilingual is Multilingual BERT?","created":"2019-06-04","cited_by_count":645},{"id":"2405.01470","title":"WildChat: 1M ChatGPT Interaction Logs in the Wild","created":"2024-05-02","cited_by_count":629},{"id":"2106.03193","title":"The FLORES-101 Evaluation Benchmark for Low-Resource and Multilingual Machine Translation","created":"2021-06-06","cited_by_count":560},{"id":"2210.03057","title":"Language Models are Multilingual Chain-of-Thought Reasoners","created":"2022-10-06","cited_by_count":530},{"id":"2105.13626","title":"ByT5: Towards a token-free future with pre-trained byte-to-byte models","created":"2021-05-28","cited_by_count":509},{"id":"2309.11998","title":"LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation Dataset","created":"2023-09-21","cited_by_count":461},{"id":"2312.15685","title":"What Makes Good Data for Alignment? A Comprehensive Study of Automatic Data Selection in Instruction Tuning","created":"2023-12-25","cited_by_count":364},{"id":"2005.00333","title":"XCOPA: A Multilingual Dataset for Causal Commonsense Reasoning","created":"2020-05-01","cited_by_count":333},{"id":"2309.00941","title":"Emergent Linear Representations in World Models of Self-Supervised Sequence Models","created":"2023-09-02","cited_by_count":319},{"id":"2304.08177","title":"Efficient and Effective Text Encoding for Chinese LLaMA and Alpaca","created":"2023-04-17","cited_by_count":305},{"id":"2402.07827","title":"Aya Model: An Instruction Finetuned Open-Access Multilingual Language Model","created":"2024-02-12","cited_by_count":295},{"id":"2402.10588","title":"Do Llamas Work in English? On the Latent Language of Multilingual Transformers","created":"2024-02-16","cited_by_count":281},{"id":"2004.05986","title":"CLUE: A Chinese Language Understanding Evaluation Benchmark","created":"2020-04-13","cited_by_count":278},{"id":"2112.10668","title":"Few-shot Learning with Multilingual Language Models","created":"2021-12-20","cited_by_count":278},{"id":"2004.11867","title":"Improving Massively Multilingual Neural Machine Translation and Zero-Shot Translation","created":"2020-04-24","cited_by_count":277},{"id":"2402.16827","title":"A Survey on Data Selection for Language Models","created":"2024-02-26","cited_by_count":236},{"id":"2307.16039","title":"Okapi: Instruction-tuned Large Language Models in Multiple Languages with Reinforcement Learning from Human Feedback","created":"2023-07-29","cited_by_count":190},{"id":"2401.01967","title":"A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity","created":"2024-01-03","cited_by_count":185},{"id":"1912.07840","title":"Cross-Lingual Ability of Multilingual BERT: An Empirical Study","created":"2019-12-17","cited_by_count":182},{"id":"2010.05874","title":"Gradient Vaccine: Investigating and Improving Multi-task Optimization in Massively Multilingual Models","created":"2020-10-12","cited_by_count":169},{"id":"2304.04675","title":"Multilingual Machine Translation with Large Language Models: Empirical Results and Analysis","created":"2023-04-10","cited_by_count":160},{"id":"2402.18815","title":"How do Large Language Models Handle Multilingualism?","created":"2024-02-29","cited_by_count":150},{"id":"1805.06297","title":"A robust self-learning method for fully unsupervised cross-lingual mappings of word embeddings","created":"2018-05-16","cited_by_count":146},{"id":"1706.04902","title":"A Survey Of Cross-lingual Word Embedding Models","created":"2017-06-15","cited_by_count":143},{"id":"2204.07580","title":"mGPT: Few-Shot Learners Go Multilingual","created":"2022-04-15","cited_by_count":142},{"id":"2003.12815","title":"Efficient Domain Generalization via Common-Specific Low-Rank Decomposition","created":"2020-03-28","cited_by_count":134},{"id":"2402.16438","title":"Language-Specific Neurons: The Key to Multilingual Capabilities in Large Language Models","created":"2024-02-26","cited_by_count":126},{"id":"2002.03518","title":"Multilingual Alignment of Contextual Word Representations","created":"2020-02-10","cited_by_count":114},{"id":"2310.14799","title":"Cross-lingual Prompting: Improving Zero-shot Chain-of-Thought Reasoning across Languages","created":"2023-10-23","cited_by_count":97},{"id":"2309.04766","title":"SeaEval for Multilingual Foundation Models: From Cross-Lingual Alignment to Cultural Reasoning","created":"2023-09-09","cited_by_count":94},{"id":"2402.17811","title":"TruthX: Alleviating Hallucinations by Editing Large Language Models in Truthful Space","created":"2024-02-27","cited_by_count":91},{"id":"2004.05160","title":"On the Language Neutrality of Pre-trained Multilingual Representations","created":"2020-04-09","cited_by_count":85},{"id":"2404.02431","title":"On the Multilingual Ability of Decoder-based Pre-trained Language Models: Finding and Controlling Language-Specific Neurons","created":"2024-04-03","cited_by_count":83},{"id":"2305.15011","title":"Bactrian-X: Multilingual Replicable Instruction-Following Models with Low-Rank Adaptation","created":"2023-05-24","cited_by_count":81},{"id":"1902.09492","title":"Cross-Lingual Alignment of Contextual Word Embeddings, with Applications to Zero-shot Dependency Parsing","created":"2019-02-25","cited_by_count":70},{"id":"2308.04948","title":"Extrapolating Large Language Models to Non-English by Aligning Languages","created":"2023-08-09","cited_by_count":69},{"id":"2305.12281","title":"Lifelong Language Pretraining with Distribution-Specialized Experts","created":"2023-05-20","cited_by_count":66},{"id":"2307.06018","title":"PolyLM: An Open Source Polyglot Large Language Model","created":"2023-07-12","cited_by_count":64},{"id":"2308.13198","title":"Journey to the Center of the Knowledge Neurons: Discoveries of Language-Independent Knowledge Neurons and Degenerate Knowledge Neurons","created":"2023-08-25","cited_by_count":56},{"id":"2106.10715","title":"CPM-2: Large-scale Cost-effective Pre-trained Language Models","created":"2021-06-20","cited_by_count":52},{"id":"2308.12038","title":"Large Multilingual Models Pivot Zero-Shot Multimodal Learning across Languages","created":"2023-08-23","cited_by_count":52},{"id":"2406.01771","title":"LLMs Beyond English: Scaling the Multilingual Capability of LLMs with Cross-Lingual Feedback","created":"2024-06-03","cited_by_count":51},{"id":"2310.12418","title":"The Shifted and The Overlooked: A Task-oriented Investigation of User-GPT Interactions","created":"2023-10-19","cited_by_count":45},{"id":"2306.10968","title":"BayLing: Bridging Cross-lingual Alignment and Instruction Following through Interactive Translation for Large Language Models","created":"2023-06-19","cited_by_count":42},{"id":"2309.07098","title":"Mitigating Hallucinations and Off-target Machine Translation with Source-Contrastive and Language-Contrastive Decoding","created":"2023-09-13","cited_by_count":42},{"id":"2310.16248","title":"GlotLID: Language Identification for Low-Resource Languages","created":"2023-10-24","cited_by_count":39},{"id":"2401.10440","title":"Breaking the Curse of Multilinguality with Cross-lingual Expert Language Models","created":"2024-01-19","cited_by_count":38},{"id":"2402.12204","title":"Enhancing Multilingual Capabilities of Large Language Models through Self-Distillation from Resource-Rich Languages","created":"2024-02-19","cited_by_count":36},{"id":"2406.01252","title":"Towards Scalable Automated Alignment of LLMs: A Survey","created":"2024-06-03","cited_by_count":35},{"id":"2402.18913","title":"AdaMergeX: Cross-Lingual Transfer with Large Language Models via Adaptive Adapter Merging","created":"2024-02-29","cited_by_count":34},{"id":"2311.08089","title":"Improving In-context Learning of Multilingual Generative Language Models with Cross-lingual Alignment","created":"2023-11-14","cited_by_count":33},{"id":"2406.02301","title":"mCoT: Multilingual Instruction Tuning for Reasoning Consistency in Language Models","created":"2024-06-04","cited_by_count":33},{"id":"2406.09265","title":"Sharing Matters: Analysing Neurons Across Languages and Tasks in LLMs","created":"2024-06-13","cited_by_count":33},{"id":"2304.10453","title":"Phoenix: Democratizing ChatGPT across Languages","created":"2023-04-20","cited_by_count":32},{"id":"2403.10258","title":"Is Translation All You Need? A Study on Solving Multilingual Tasks with Large Language Models","created":"2024-03-15","cited_by_count":31},{"id":"2401.14280","title":"RomanSetu: Efficiently unlocking multilingual capabilities of Large Language Models via Romanization","created":"2024-01-25","cited_by_count":29},{"id":"2401.13303","title":"MaLA-500: Massive Language Adaptation of Large Language Models","created":"2024-01-24","cited_by_count":28},{"id":"2403.03814","title":"Evaluating the Elementary Multilingual Capabilities of Large Language Models with MultiQ","created":"2024-03-06","cited_by_count":27},{"id":"2311.15131","title":"Localizing Lying in Llama: Understanding Instructed Dishonesty on True-False Questions Through Prompting, Probing, and Patching","created":"2023-11-25","cited_by_count":24},{"id":"2404.04042","title":"Teaching Llama a New Language Through Cross-Lingual Knowledge Transfer","created":"2024-04-05","cited_by_count":23},{"id":"2402.14700","title":"Unveiling Linguistic Regions in Large Language Models","created":"2024-02-22","cited_by_count":22},{"id":"1902.03499","title":"Multilingual Neural Machine Translation With Soft Decoupled Encoding","created":"2019-02-09","cited_by_count":21},{"id":"2404.12444","title":"mOthello: When Do Cross-Lingual Representation Alignment and Cross-Lingual Transfer Emerge in Multilingual Models?","created":"2024-04-18","cited_by_count":21},{"id":"2312.04333","title":"Is Bigger and Deeper Always Better? Probing LLaMA Across Scales and Layers","created":"2023-12-07","cited_by_count":20},{"id":"2401.05792","title":"Discovering Low-rank Subspaces for Language-agnostic Multilingual Representations","created":"2024-01-11","cited_by_count":19},{"id":"1811.01124","title":"Unsupervised Hyperalignment for Multilingual Word Embeddings","created":"2018-11-02","cited_by_count":17},{"id":"2109.04727","title":"A Simple and Effective Method To Eliminate the Self Language Bias in Multilingual Representations","created":"2021-09-10","cited_by_count":17},{"id":"2110.02600","title":"Sequential Reptile: Inter-Task Gradient Alignment for Multilingual Learning","created":"2021-10-06","cited_by_count":16},{"id":"2310.18696","title":"Probing LLMs for Joint Encoding of Linguistic Categories","created":"2023-10-28","cited_by_count":9},{"id":"2405.16964","title":"Exploring the LLM Journey from Cognition to Expression with Linear Representations","created":"2024-05-27","cited_by_count":5},{"id":"2407.01853","title":"Improving Multilingual Instruction Finetuning via Linguistically Natural and Diverse Datasets","created":"2024-07-01","cited_by_count":4}],"next_cursor":null}