{"list":"other","total":60,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"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":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2004.04906","title":"Dense Passage Retrieval for Open-Domain Question Answering","created":"2020-04-10","cited_by_count":3824},{"id":"1809.09600","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","created":"2018-09-25","cited_by_count":3754},{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"1606.08415","title":"Gaussian Error Linear Units (GELUs)","created":"2016-06-27","cited_by_count":3502},{"id":"1611.01144","title":"Categorical Reparameterization with Gumbel-Softmax","created":"2016-11-03","cited_by_count":2739},{"id":"2307.08691","title":"FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning","created":"2023-07-17","cited_by_count":2598},{"id":"1910.03771","title":"HuggingFace's Transformers: State-of-the-art Natural Language Processing","created":"2019-10-09","cited_by_count":2218},{"id":"1611.09268","title":"MS MARCO: A Human Generated MAchine Reading COmprehension Dataset","created":"2016-11-28","cited_by_count":1605},{"id":"2004.10964","title":"Don't Stop Pretraining: Adapt Language Models to Domains and Tasks","created":"2020-04-23","cited_by_count":1565},{"id":"1803.05355","title":"FEVER: a large-scale dataset for Fact Extraction and VERification","created":"2018-03-14","cited_by_count":1375},{"id":"2306.00978","title":"AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration","created":"2023-06-01","cited_by_count":1298},{"id":"2104.08663","title":"BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models","created":"2021-04-17","cited_by_count":1252},{"id":"2007.00808","title":"Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval","created":"2020-07-01","cited_by_count":849},{"id":"2004.14974","title":"Fact or Fiction: Verifying Scientific Claims","created":"2020-04-30","cited_by_count":554},{"id":"2412.13663","title":"Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference","created":"2024-12-18","cited_by_count":554},{"id":"2405.17428","title":"NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models","created":"2024-05-27","cited_by_count":472},{"id":"2112.07899","title":"Large Dual Encoders Are Generalizable Retrievers","created":"2021-12-15","cited_by_count":456},{"id":"2004.07180","title":"SPECTER: Document-level Representation Learning using Citation-informed Transformers","created":"2020-04-15","cited_by_count":430},{"id":"2010.08191","title":"RocketQA: An Optimized Training Approach to Dense Passage Retrieval for Open-Domain Question Answering","created":"2020-10-16","cited_by_count":413},{"id":"2404.05961","title":"LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders","created":"2024-04-09","cited_by_count":404},{"id":"2308.07107","title":"Large Language Models for Information Retrieval: A Survey","created":"2023-08-14","cited_by_count":331},{"id":"2405.09673","title":"LoRA Learns Less and Forgets Less","created":"2024-05-15","cited_by_count":328},{"id":"2310.08319","title":"Fine-Tuning LLaMA for Multi-Stage Text Retrieval","created":"2023-10-12","cited_by_count":272},{"id":"2010.06467","title":"Pretrained Transformers for Text Ranking: BERT and Beyond","created":"2020-10-13","cited_by_count":267},{"id":"2212.09720","title":"The case for 4-bit precision: k-bit Inference Scaling Laws","created":"2022-12-19","cited_by_count":251},{"id":"2202.08904","title":"SGPT: GPT Sentence Embeddings for Semantic Search","created":"2022-02-17","cited_by_count":204},{"id":"2108.05540","title":"Unsupervised Corpus Aware Language Model Pre-training for Dense Passage Retrieval","created":"2021-08-12","cited_by_count":203},{"id":"2012.00614","title":"CLIMATE-FEVER: A Dataset for Verification of Real-World Climate Claims","created":"2020-12-01","cited_by_count":196},{"id":"2010.02666","title":"Improving Efficient Neural Ranking Models with Cross-Architecture Knowledge Distillation","created":"2020-10-06","cited_by_count":145},{"id":"1905.09217","title":"Deeper Text Understanding for IR with Contextual Neural Language Modeling","created":"2019-05-22","cited_by_count":113},{"id":"2205.04733","title":"From Distillation to Hard Negative Sampling: Making Sparse Neural IR Models More Effective","created":"2022-05-10","cited_by_count":98},{"id":"2207.02578","title":"SimLM: Pre-training with Representation Bottleneck for Dense Passage Retrieval","created":"2022-07-06","cited_by_count":90},{"id":"2403.06789","title":"SPLADE-v3: New baselines for SPLADE","created":"2024-03-11","cited_by_count":72},{"id":"2104.12016","title":"Learning Passage Impacts for Inverted Indexes","created":"2021-04-24","cited_by_count":68},{"id":"2102.10073","title":"Pyserini: An Easy-to-Use Python Toolkit to Support Replicable IR Research with Sparse and Dense Representations","created":"2021-02-19","cited_by_count":60},{"id":"2403.15447","title":"Decoding Compressed Trust: Scrutinizing the Trustworthiness of Efficient LLMs Under Compression","created":"2024-03-18","cited_by_count":57},{"id":"2009.13013","title":"SPARTA: Efficient Open-Domain Question Answering via Sparse Transformer Matching Retrieval","created":"2020-09-28","cited_by_count":50},{"id":"2203.05765","title":"Tevatron: An Efficient and Flexible Toolkit for Dense Retrieval","created":"2022-03-11","cited_by_count":47},{"id":"2004.05665","title":"Minimizing FLOPs to Learn Efficient Sparse Representations","created":"2020-04-12","cited_by_count":46},{"id":"2010.00768","title":"SparTerm: Learning Term-based Sparse Representation for Fast Text Retrieval","created":"2020-10-02","cited_by_count":45},{"id":"2407.04965","title":"Beyond Perplexity: Multi-dimensional Safety Evaluation of LLM Compression","created":"2024-07-06","cited_by_count":33},{"id":"2404.18424","title":"PromptReps: Prompting Large Language Models to Generate Dense and Sparse Representations for Zero-Shot Document Retrieval","created":"2024-04-29","cited_by_count":30},{"id":"2004.14245","title":"Expansion via Prediction of Importance with Contextualization","created":"2020-04-29","cited_by_count":26},{"id":"2404.18812","title":"Efficient Inverted Indexes for Approximate Retrieval over Learned Sparse Representations","created":"2024-04-29","cited_by_count":24},{"id":"2502.14822","title":"A Survey of Model Architectures in Information Retrieval","created":"2025-02-20","cited_by_count":20},{"id":"2403.18276","title":"RankMamba: Benchmarking Mamba's Document Ranking Performance in the Era of Transformers","created":"2024-03-27","cited_by_count":15},{"id":"2302.06587","title":"SLIM: Sparsified Late Interaction for Multi-Vector Retrieval with Inverted Indexes","created":"2023-02-13","cited_by_count":12},{"id":"2312.14335","title":"Context-aware Decoding Reduces Hallucination in Query-focused Summarization","created":"2023-12-21","cited_by_count":11},{"id":"2412.14354","title":"State Space Models are Strong Text Rerankers","created":"2024-12-18","cited_by_count":10},{"id":"2304.11721","title":"A Lightweight Constrained Generation Alternative for Query-focused Summarization","created":"2023-04-23","cited_by_count":8},{"id":"2408.11119","title":"Mistral-SPLADE: LLMs for better Learned Sparse Retrieval","created":"2024-08-20","cited_by_count":8},{"id":"2411.04403","title":"Towards Competitive Search Relevance For Inference-Free Learned Sparse Retrievers","created":"2024-11-07","cited_by_count":8}],"next_cursor":null}