{"total":71,"rows":[{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795,"area":null},{"id":"2203.06904","title":"Delta Tuning: A Comprehensive Study of Parameter Efficient Methods for Pre-trained Language Models","created":"2022-03-14","cited_by_count":180,"area":null},{"id":"2101.00774","title":"Retrieving and Reading: A Comprehensive Survey on Open-domain Question Answering","created":"2021-01-04","cited_by_count":178,"area":null},{"id":"2104.08835","title":"CrossFit: A Few-shot Learning Challenge for Cross-task Generalization in NLP","created":"2021-04-18","cited_by_count":142,"area":null},{"id":"2105.09680","title":"KLUE: Korean Language Understanding Evaluation","created":"2021-05-20","cited_by_count":114,"area":null},{"id":"2302.03202","title":"Exploring the Benefits of Training Expert Language Models over Instruction Tuning","created":"2023-02-07","cited_by_count":80,"area":null},{"id":"2104.08247","title":"What to Pre-Train on? Efficient Intermediate Task Selection","created":"2021-04-16","cited_by_count":63,"area":null},{"id":"2205.00415","title":"Don't Blame the Annotator: Bias Already Starts in the Annotation Instructions","created":"2022-05-01","cited_by_count":47,"area":null},{"id":"2305.09137","title":"Pre-Training to Learn in Context","created":"2023-05-16","cited_by_count":42,"area":null},{"id":"2602.06855","title":"AIRS-Bench: a Suite of Tasks for Frontier AI Research Science Agents","created":"2026-02-06","cited_by_count":38,"area":"agents"},{"id":"2106.00872","title":"On the Efficacy of Adversarial Data Collection for Question Answering: Results from a Large-Scale Randomized Study","created":"2021-06-02","cited_by_count":31,"area":null},{"id":"2402.11597","title":"Multi-Task Inference: Can Large Language Models Follow Multiple Instructions at Once?","created":"2024-02-18","cited_by_count":30,"area":null},{"id":"2101.10421","title":"English Machine Reading Comprehension Datasets: A Survey","created":"2021-01-25","cited_by_count":26,"area":null},{"id":"2110.07867","title":"Exploring Universal Intrinsic Task Subspace via Prompt Tuning","created":"2021-10-15","cited_by_count":25,"area":null},{"id":"2210.12517","title":"Exploring The Landscape of Distributional Robustness for Question Answering Models","created":"2022-10-22","cited_by_count":23,"area":null},{"id":"2203.08304","title":"Hyperdecoders: Instance-specific decoders for multi-task NLP","created":"2022-03-15","cited_by_count":22,"area":null},{"id":"2109.07954","title":"Improving Unsupervised Question Answering via Summarization-Informed Question Generation","created":"2021-09-16","cited_by_count":21,"area":null},{"id":"2305.01812","title":"Post-Abstention: Towards Reliably Re-Attempting the Abstained Instances in QA","created":"2023-05-02","cited_by_count":20,"area":null},{"id":"2407.21530","title":"Data Contamination Report from the 2024 CONDA Shared Task","created":"2024-07-31","cited_by_count":20,"area":null},{"id":"2501.16075","title":"PISCO: Pretty Simple Compression for Retrieval-Augmented Generation","created":"2025-01-27","cited_by_count":20,"area":"rag"},{"id":"2106.08190","title":"Question Answering Infused Pre-training of General-Purpose Contextualized Representations","created":"2021-06-15","cited_by_count":19,"area":null},{"id":"2109.13880","title":"Single-dataset Experts for Multi-dataset Question Answering","created":"2021-09-28","cited_by_count":15,"area":null},{"id":"2112.01922","title":"MetaQA: Combining Expert Agents for Multi-Skill Question Answering","created":"2021-12-03","cited_by_count":15,"area":null},{"id":"2210.09175","title":"Learning Instructions with Unlabeled Data for Zero-Shot Cross-Task Generalization","created":"2022-10-17","cited_by_count":15,"area":null},{"id":"2310.19240","title":"M4LE: A Multi-Ability Multi-Range Multi-Task Multi-Domain Long-Context Evaluation Benchmark for Large Language Models","created":"2023-10-30","cited_by_count":15,"area":null},{"id":"2308.12539","title":"CALM : A Multi-task Benchmark for Comprehensive Assessment of Language Model Bias","created":"2023-08-24","cited_by_count":14,"area":null},{"id":"2311.13133","title":"LIMIT: Less Is More for Instruction Tuning Across Evaluation Paradigms","created":"2023-11-22","cited_by_count":14,"area":null},{"id":"2510.08907","title":"Autoencoding-Free Context Compression for LLMs via Contextual Semantic Anchors","created":"2025-10-10","cited_by_count":14,"area":"inference"},{"id":"2205.12701","title":"Eliciting and Understanding Cross-Task Skills with Task-Level Mixture-of-Experts","created":"2022-05-25","cited_by_count":12,"area":"moe"},{"id":"2206.05658","title":"Improving Pre-trained Language Model Fine-tuning with Noise Stability Regularization","created":"2022-06-12","cited_by_count":12,"area":null},{"id":"2302.08143","title":"Learning to Initialize: Can Meta Learning Improve Cross-task Generalization in Prompt Tuning?","created":"2023-02-16","cited_by_count":11,"area":null},{"id":"2210.04320","title":"QAScore -- An Unsupervised Unreferenced Metric for the Question Generation Evaluation","created":"2022-10-09","cited_by_count":9,"area":null},{"id":"2409.14364","title":"Position IDs Matter: An Enhanced Position Layout for Efficient Context Compression in Large Language Models","created":"2024-09-22","cited_by_count":9,"area":"inference"},{"id":"2205.11024","title":"Vector-Quantized Input-Contextualized Soft Prompts for Natural Language Understanding","created":"2022-05-23","cited_by_count":7,"area":null},{"id":"2210.11705","title":"Efficiently Tuned Parameters are Task Embeddings","created":"2022-10-21","cited_by_count":7,"area":null},{"id":"2212.09912","title":"Tokenization Consistency Matters for Generative Models on Extractive NLP Tasks","created":"2022-12-19","cited_by_count":7,"area":null},{"id":"2510.20797","title":"No Mean Feat: Simple, Strong Baselines for Context Compression","created":"2025-10-23","cited_by_count":7,"area":"inference"},{"id":"2203.13693","title":"UKP-SQUARE: An Online Platform for Question Answering Research","created":"2022-03-25","cited_by_count":6,"area":null},{"id":"2212.10815","title":"ZEROTOP: Zero-Shot Task-Oriented Semantic Parsing using Large Language Models","created":"2022-12-21","cited_by_count":6,"area":null},{"id":"2505.09519","title":"PT-MoE: An Efficient Finetuning Framework for Integrating Mixture-of-Experts into Prompt Tuning","created":"2025-05-14","cited_by_count":6,"area":"moe"},{"id":"2205.07257","title":"Not to Overfit or Underfit the Source Domains? An Empirical Study of Domain Generalization in Question Answering","created":"2022-05-15","cited_by_count":5,"area":null},{"id":"2212.01476","title":"NarraSum: A Large-Scale Dataset for Abstractive Narrative Summarization","created":"2022-12-02","cited_by_count":5,"area":null},{"id":"2307.02738","title":"RecallM: An Adaptable Memory Mechanism with Temporal Understanding for Large Language Models","created":"2023-07-06","cited_by_count":5,"area":null},{"id":"2312.17055","title":"Beyond Output Matching: Bidirectional Alignment for Enhanced In-Context Learning","created":"2023-12-28","cited_by_count":5,"area":null},{"id":"2101.06326","title":"Grid Search Hyperparameter Benchmarking of BERT, ALBERT, and LongFormer on DuoRC","created":"2021-01-15","cited_by_count":4,"area":null},{"id":"2208.10813","title":"Unsupervised Question Answering via Answer Diversifying","created":"2022-08-23","cited_by_count":4,"area":null},{"id":"2507.18584","title":"AQuilt: Weaving Logic and Self-Inspection into Low-Cost, High-Relevance Data Synthesis for Specialist LLMs","created":"2025-07-24","cited_by_count":4,"area":"synth"},{"id":"2203.11054","title":"Targeted Extraction of Temporal Facts from Textual Resources for Improved Temporal Question Answering over Knowledge Bases","created":"2022-03-21","cited_by_count":3,"area":null},{"id":"2504.02411","title":"Adapting Large Language Models for Multi-Domain Retrieval-Augmented-Generation","created":"2025-04-03","cited_by_count":3,"area":"rag"},{"id":"2605.09463","title":"Beyond Position Bias: Shifting Context Compression from Position-Driven to Semantic-Driven","created":"2026-05-10","cited_by_count":3,"area":"inference"},{"id":"2107.00368","title":"Ensemble Learning-Based Approach for Improving Generalization Capability of Machine Reading Comprehension Systems","created":"2021-07-01","cited_by_count":2,"area":null},{"id":"2206.12388","title":"QAGAN: Adversarial Approach To Learning Domain Invariant Language Features","created":"2022-06-24","cited_by_count":2,"area":null},{"id":"2210.03029","title":"Efficiently Enhancing Zero-Shot Performance of Instruction Following Model via Retrieval of Soft Prompt","created":"2022-10-06","cited_by_count":2,"area":null},{"id":"2212.04755","title":"From Cloze to Comprehension: Retrofitting Pre-trained Masked Language Model to Pre-trained Machine Reader","created":"2022-12-09","cited_by_count":2,"area":null},{"id":"2301.01064","title":"PIE-QG: Paraphrased Information Extraction for Unsupervised Question Generation from Small Corpora","created":"2023-01-03","cited_by_count":2,"area":null},{"id":"2305.14569","title":"Few-shot Unified Question Answering: Tuning Models or Prompts?","created":"2023-05-23","cited_by_count":2,"area":"lr"},{"id":"2402.14522","title":"Towards Unified Task Embeddings Across Multiple Models: Bridging the Gap for Prompt-Based Large Language Models and Beyond","created":"2024-02-22","cited_by_count":2,"area":null},{"id":"2408.10536","title":"Synergistic Approach for Simultaneous Optimization of Monolingual, Cross-lingual, and Multilingual Information Retrieval","created":"2024-08-20","cited_by_count":2,"area":null},{"id":"2409.18446","title":"Exploring Language Model Generalization in Low-Resource Extractive QA","created":"2024-09-27","cited_by_count":2,"area":null},{"id":"2605.01959","title":"Flexi-LoRA with Input-Adaptive Ranks: Efficient Finetuning for Speech and Reasoning Tasks","created":"2026-05-03","cited_by_count":2,"area":"lr"},{"id":"2206.10265","title":"KnowDA: All-in-One Knowledge Mixture Model for Data Augmentation in Low-Resource NLP","created":"2022-06-21","cited_by_count":1,"area":null},{"id":"2210.13311","title":"Different Tunes Played with Equal Skill: Exploring a Unified Optimization Subspace for Delta Tuning","created":"2022-10-24","cited_by_count":1,"area":null},{"id":"2310.13409","title":"Explicit Alignment and Many-to-many Entailment Based Reasoning for Conversational Machine Reading","created":"2023-10-20","cited_by_count":1,"area":null},{"id":"2401.09168","title":"Fine-tuning Strategies for Domain Specific Question Answering under Low Annotation Budget Constraints","created":"2024-01-17","cited_by_count":1,"area":null},{"id":"2402.06220","title":"A Unified Causal View of Instruction Tuning","created":"2024-02-09","cited_by_count":1,"area":null},{"id":"2404.05250","title":"Interpreting Themes from Educational Stories","created":"2024-04-08","cited_by_count":1,"area":null},{"id":"2204.09598","title":"Build a Robust QA System with Transformer-based Mixture of Experts","created":"2022-03-20","cited_by_count":0,"area":"moe"},{"id":"2311.09605","title":"Measuring and Improving Attentiveness to Partial Inputs with Counterfactuals","created":"2023-11-16","cited_by_count":0,"area":null},{"id":"2512.15658","title":"PPSEBM: An Energy-Based Model with Progressive Parameter Selection for Continual Learning","created":"2025-12-17","cited_by_count":0,"area":null},{"id":"2608.29790","title":"HiVe: Beyond Static Prompts for Multitask Learning via Hierarchy-based Vertical Mixture-of-Experts","created":"2026-08-30","cited_by_count":0,"area":"moe"},{"id":"2610.12837","title":"COFFEQA: Counterfactual-Guided Few-Shot Distillation for LLM Question Answering","created":"2026-10-09","cited_by_count":0,"area":"distill"}],"next_cursor":null}