{"list":"other","total":64,"rows":[{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"1706.04599","title":"On Calibration of Modern Neural Networks","created":"2017-06-14","cited_by_count":4960},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780},{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"2309.16609","title":"Qwen Technical Report","created":"2023-09-28","cited_by_count":3344},{"id":"1509.01626","title":"Character-level Convolutional Networks for Text Classification","created":"2015-09-04","cited_by_count":2330},{"id":"2407.10671","title":"Qwen2 Technical Report","created":"2024-07-15","cited_by_count":2120},{"id":"2206.04615","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","created":"2022-06-09","cited_by_count":1998},{"id":"2210.09261","title":"Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them","created":"2022-10-17","cited_by_count":1807},{"id":"2304.01373","title":"Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling","created":"2023-04-03","cited_by_count":1786},{"id":"2202.12837","title":"Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?","created":"2022-02-25","cited_by_count":1434},{"id":"2102.09690","title":"Calibrate Before Use: Improving Few-Shot Performance of Language Models","created":"2021-02-19","cited_by_count":1392},{"id":"2306.00978","title":"AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration","created":"2023-06-01","cited_by_count":1298},{"id":"2101.06804","title":"What Makes Good In-Context Examples for GPT-$3$?","created":"2021-01-17","cited_by_count":1195},{"id":"2104.08786","title":"Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity","created":"2021-04-18","cited_by_count":1135},{"id":"2304.15004","title":"Are Emergent Abilities of Large Language Models a Mirage?","created":"2023-04-28","cited_by_count":523},{"id":"2102.01454","title":"MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence Frontiers","created":"2021-02-02","cited_by_count":470},{"id":"2110.15943","title":"MetaICL: Learning to Learn In Context","created":"2021-10-29","cited_by_count":454},{"id":"2303.03846","title":"Larger language models do in-context learning differently","created":"2023-03-07","cited_by_count":394},{"id":"2102.06701","title":"Explaining Neural Scaling Laws","created":"2021-02-12","cited_by_count":363},{"id":"1307.5336","title":"Good Debt or Bad Debt: Detecting Semantic Orientations in Economic Texts","created":"2013-07-19","cited_by_count":310},{"id":"2209.01975","title":"Selective Annotation Makes Language Models Better Few-Shot Learners","created":"2022-09-05","cited_by_count":243},{"id":"2212.12017","title":"OPT-IML: Scaling Language Model Instruction Meta Learning through the Lens of Generalization","created":"2022-12-22","cited_by_count":236},{"id":"2305.14160","title":"Label Words are Anchors: An Information Flow Perspective for Understanding In-Context Learning","created":"2023-05-23","cited_by_count":236},{"id":"2212.04037","title":"Demystifying Prompts in Language Models via Perplexity Estimation","created":"2022-12-08","cited_by_count":216},{"id":"2212.10559","title":"Why Can GPT Learn In-Context? Language Models Implicitly Perform Gradient Descent as Meta-Optimizers","created":"2022-12-20","cited_by_count":204},{"id":"1809.04444","title":"Hate Speech Dataset from a White Supremacy Forum","created":"2018-09-12","cited_by_count":198},{"id":"2108.04106","title":"Noisy Channel Language Model Prompting for Few-Shot Text Classification","created":"2021-08-09","cited_by_count":165},{"id":"2212.10375","title":"Self-Adaptive In-Context Learning: An Information Compression Perspective for In-Context Example Selection and Ordering","created":"2022-12-20","cited_by_count":161},{"id":"2305.09731","title":"What In-Context Learning \"Learns\" In-Context: Disentangling Task Recognition and Task Learning","created":"2023-05-16","cited_by_count":152},{"id":"2305.04320","title":"Unified Demonstration Retriever for In-Context Learning","created":"2023-05-07","cited_by_count":142},{"id":"2303.07895","title":"The Learnability of In-Context Learning","created":"2023-03-14","cited_by_count":127},{"id":"2205.12685","title":"Ground-Truth Labels Matter: A Deeper Look into Input-Label Demonstrations","created":"2022-05-25","cited_by_count":116},{"id":"2310.05249","title":"In-Context Convergence of Transformers","created":"2023-10-08","cited_by_count":115},{"id":"2302.13539","title":"Finding Support Examples for In-Context Learning","created":"2023-02-27","cited_by_count":104},{"id":"2309.17249","title":"Batch Calibration: Rethinking Calibration for In-Context Learning and Prompt Engineering","created":"2023-09-29","cited_by_count":94},{"id":"2305.19148","title":"Mitigating Label Biases for In-context Learning","created":"2023-05-28","cited_by_count":89},{"id":"2401.06766","title":"Mind Your Format: Towards Consistent Evaluation of In-Context Learning Improvements","created":"2024-01-12","cited_by_count":83},{"id":"2212.06713","title":"Structured Prompting: Scaling In-Context Learning to 1,000 Examples","created":"2022-12-13","cited_by_count":81},{"id":"2310.10638","title":"In-context Pretraining: Language Modeling Beyond Document Boundaries","created":"2023-10-16","cited_by_count":79},{"id":"2305.08298","title":"Symbol tuning improves in-context learning in language models","created":"2023-05-15","cited_by_count":75},{"id":"2310.09881","title":"In-Context Learning with Iterative Demonstration Selection","created":"2023-10-15","cited_by_count":74},{"id":"2209.07661","title":"On the Relation between Sensitivity and Accuracy in In-context Learning","created":"2022-09-16","cited_by_count":72},{"id":"2205.10183","title":"Prototypical Calibration for Few-shot Learning of Language Models","created":"2022-05-20","cited_by_count":58},{"id":"2307.12375","title":"In-Context Learning Learns Label Relationships but Is Not Conventional Learning","created":"2023-07-23","cited_by_count":51},{"id":"2303.13824","title":"$k$NN Prompting: Beyond-Context Learning with Calibration-Free Nearest Neighbor Inference","created":"2023-03-24","cited_by_count":47},{"id":"2402.10738","title":"Let's Learn Step by Step: Enhancing In-Context Learning Ability with Curriculum Learning","created":"2024-02-16","cited_by_count":47},{"id":"2405.19592","title":"Why Larger Language Models Do In-context Learning Differently?","created":"2024-05-30","cited_by_count":45},{"id":"2305.09137","title":"Pre-Training to Learn in Context","created":"2023-05-16","cited_by_count":42},{"id":"2306.15091","title":"Understanding In-Context Learning via Supportive Pretraining Data","created":"2023-06-26","cited_by_count":41},{"id":"2401.15530","title":"An Information-Theoretic Analysis of In-Context Learning","created":"2024-01-28","cited_by_count":40},{"id":"2310.20046","title":"Which Examples to Annotate for In-Context Learning? Towards Effective and Efficient Selection","created":"2023-10-30","cited_by_count":37},{"id":"2402.11639","title":"In-Context Learning with Transformers: Softmax Attention Adapts to Function Lipschitzness","created":"2024-02-18","cited_by_count":22},{"id":"2310.10266","title":"Generative Calibration for In-context Learning","created":"2023-10-16","cited_by_count":20},{"id":"2410.04468","title":"Revisiting In-context Learning Inference Circuit in Large Language Models","created":"2024-10-06","cited_by_count":17},{"id":"2401.12406","title":"Enhancing In-context Learning via Linear Probe Calibration","created":"2024-01-22","cited_by_count":16},{"id":"2406.04216","title":"What Do Language Models Learn in Context? The Structured Task Hypothesis","created":"2024-06-06","cited_by_count":13},{"id":"2402.11750","title":"In-Context Learning Demonstration Selection via Influence Analysis","created":"2024-02-19","cited_by_count":11},{"id":"2406.16535","title":"Token-based Decision Criteria Are Suboptimal in In-context Learning","created":"2024-06-24","cited_by_count":9},{"id":"2312.07405","title":"ICL Markup: Structuring In-Context Learning using Soft-Token Tags","created":"2023-12-12","cited_by_count":5},{"id":"2402.05515","title":"NoisyICL: A Little Noise in Model Parameters Calibrates In-context Learning","created":"2024-02-08","cited_by_count":4}],"next_cursor":null}