{"total":89,"rows":[{"id":"2202.12837","title":"Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?","created":"2022-02-25","cited_by_count":1434,"area":"lr"},{"id":"2306.01708","title":"TIES-Merging: Resolving Interference When Merging Models","created":"2023-06-02","cited_by_count":818,"area":null},{"id":"2406.04093","title":"Scaling and evaluating sparse autoencoders","created":"2024-06-06","cited_by_count":553,"area":"mechinterp"},{"id":"2312.09390","title":"Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision","created":"2023-12-14","cited_by_count":467,"area":"alignment"},{"id":"2110.15943","title":"MetaICL: Learning to Learn In Context","created":"2021-10-29","cited_by_count":454,"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":"2405.13576","title":"FlashRAG: A Modular Toolkit for Efficient Retrieval-Augmented Generation Research","created":"2024-05-22","cited_by_count":166,"area":"mllm"},{"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":"2405.07813","title":"Localizing Task Information for Improved Model Merging and Compression","created":"2024-05-13","cited_by_count":131,"area":null},{"id":"2104.08646","title":"Competency Problems: On Finding and Removing Artifacts in Language Data","created":"2021-04-17","cited_by_count":91,"area":null},{"id":"2107.12708","title":"QA Dataset Explosion: A Taxonomy of NLP Resources for Question Answering and Reading Comprehension","created":"2021-07-27","cited_by_count":91,"area":null},{"id":"2304.13007","title":"Answering Questions by Meta-Reasoning over Multiple Chains of Thought","created":"2023-04-25","cited_by_count":87,"area":"lr"},{"id":"2410.02396","title":"Parameter Competition Balancing for Model Merging","created":"2024-10-03","cited_by_count":72,"area":null},{"id":"2404.15522","title":"LogicBench: Towards Systematic Evaluation of Logical Reasoning Ability of Large Language Models","created":"2024-04-23","cited_by_count":68,"area":"lr"},{"id":"2104.08247","title":"What to Pre-Train on? Efficient Intermediate Task Selection","created":"2021-04-16","cited_by_count":63,"area":null},{"id":"2406.14491","title":"Instruction Pre-Training: Language Models are Supervised Multitask Learners","created":"2024-06-20","cited_by_count":63,"area":null},{"id":"2305.14264","title":"Active Learning Principles for In-Context Learning with Large Language Models","created":"2023-05-23","cited_by_count":54,"area":null},{"id":"2305.03695","title":"Vera: A General-Purpose Plausibility Estimation Model for Commonsense Statements","created":"2023-05-05","cited_by_count":44,"area":null},{"id":"2210.03078","title":"Rainier: Reinforced Knowledge Introspector for Commonsense Question Answering","created":"2022-10-06","cited_by_count":43,"area":null},{"id":"2305.09137","title":"Pre-Training to Learn in Context","created":"2023-05-16","cited_by_count":42,"area":null},{"id":"2410.17146","title":"LiNeS: Post-training Layer Scaling Prevents Forgetting and Enhances Model Merging","created":"2024-10-22","cited_by_count":41,"area":null},{"id":"2210.12217","title":"Entailer: Answering Questions with Faithful and Truthful Chains of Reasoning","created":"2022-10-21","cited_by_count":38,"area":null},{"id":"2204.13074","title":"Towards Teachable Reasoning Systems: Using a Dynamic Memory of User Feedback for Continual System Improvement","created":"2022-04-27","cited_by_count":37,"area":"lr"},{"id":"2312.04339","title":"Merging by Matching Models in Task Parameter Subspaces","created":"2023-12-07","cited_by_count":36,"area":null},{"id":"2310.00836","title":"Towards LogiGLUE: A Brief Survey and A Benchmark for Analyzing Logical Reasoning Capabilities of Language Models","created":"2023-10-02","cited_by_count":35,"area":"lr"},{"id":"2203.10261","title":"FaiRR: Faithful and Robust Deductive Reasoning over Natural Language","created":"2022-03-19","cited_by_count":29,"area":"lr"},{"id":"2110.07867","title":"Exploring Universal Intrinsic Task Subspace via Prompt Tuning","created":"2021-10-15","cited_by_count":25,"area":null},{"id":"2210.16433","title":"Knowledge-in-Context: Towards Knowledgeable Semi-Parametric Language Models","created":"2022-10-28","cited_by_count":24,"area":"moe"},{"id":"2210.02969","title":"Guess the Instruction! Flipped Learning Makes Language Models Stronger Zero-Shot Learners","created":"2022-10-06","cited_by_count":22,"area":null},{"id":"2210.04982","title":"REV: Information-Theoretic Evaluation of Free-Text Rationales","created":"2022-10-10","cited_by_count":22,"area":null},{"id":"2412.03881","title":"Weak-to-Strong Generalization Through the Data-Centric Lens","created":"2024-12-05","cited_by_count":21,"area":"alignment"},{"id":"2308.07336","title":"Learning Deductive Reasoning from Synthetic Corpus based on Formal Logic","created":"2023-08-11","cited_by_count":18,"area":"lr"},{"id":"2203.03073","title":"ILDAE: Instance-Level Difficulty Analysis of Evaluation Data","created":"2022-03-07","cited_by_count":17,"area":null},{"id":"2104.08620","title":"Decrypting Cryptic Crosswords: Semantically Complex Wordplay Puzzles as a Target for NLP","created":"2021-04-17","cited_by_count":16,"area":null},{"id":"2504.02620","title":"Efficient Model Editing with Task-Localized Sparse Fine-tuning","created":"2025-04-03","cited_by_count":16,"area":null},{"id":"2106.01354","title":"multiPRover: Generating Multiple Proofs for Improved Interpretability in Rule Reasoning","created":"2021-06-02","cited_by_count":15,"area":null},{"id":"2210.07471","title":"\"John is 50 years old, can his son be 65?\" Evaluating NLP Models' Understanding of Feasibility","created":"2022-10-14","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":"2305.14250","title":"Language Models with Rationality","created":"2023-05-23","cited_by_count":15,"area":null},{"id":"2310.04921","title":"Crystal: Introspective Reasoners Reinforced with Self-Feedback","created":"2023-10-07","cited_by_count":15,"area":"lr"},{"id":"2210.06277","title":"Task Compass: Scaling Multi-task Pre-training with Task Prefix","created":"2022-10-12","cited_by_count":14,"area":null},{"id":"2206.11083","title":"Investigating the Benefits of Free-Form Rationales","created":"2022-05-25","cited_by_count":13,"area":null},{"id":"2502.02464","title":"Rankify: A Comprehensive Python Toolkit for Retrieval, Re-Ranking, and Retrieval-Augmented Generation","created":"2025-02-04","cited_by_count":13,"area":"rag"},{"id":"2104.08840","title":"On the Influence of Masking Policies in Intermediate Pre-training","created":"2021-04-18","cited_by_count":12,"area":null},{"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":"2407.03181","title":"Fine-Tuning on Diverse Reasoning Chains Drives Within-Inference CoT Refinement in LLMs","created":"2024-07-03","cited_by_count":12,"area":"lr"},{"id":"2504.18992","title":"Dynamic Fisher-weighted Model Merging via Bayesian Optimization","created":"2025-04-26","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":"2305.13256","title":"TaskWeb: Selecting Better Source Tasks for Multi-task NLP","created":"2023-05-22","cited_by_count":11,"area":null},{"id":"2505.18713","title":"Neural Parameter Search for Slimmer Fine-Tuned Models and Better Transfer","created":"2025-05-24","cited_by_count":11,"area":null},{"id":"2205.10714","title":"Interpretable Proof Generation via Iterative Backward Reasoning","created":"2022-05-22","cited_by_count":9,"area":"lr"},{"id":"2210.00185","title":"Zemi: Learning Zero-Shot Semi-Parametric Language Models from Multiple Tasks","created":"2022-10-01","cited_by_count":8,"area":null},{"id":"2307.02729","title":"Text Alignment Is An Efficient Unified Model for Massive NLP Tasks","created":"2023-07-06","cited_by_count":8,"area":null},{"id":"2305.13179","title":"Teaching Probabilistic Logical Reasoning to Transformers","created":"2023-05-22","cited_by_count":7,"area":"lr"},{"id":"2307.03115","title":"KoRC: Knowledge oriented Reading Comprehension Benchmark for Deep Text Understanding","created":"2023-07-06","cited_by_count":7,"area":null},{"id":"2203.13693","title":"UKP-SQUARE: An Online Platform for Question Answering Research","created":"2022-03-25","cited_by_count":6,"area":null},{"id":"2208.01009","title":"Few-shot Adaptation Works with UnpredicTable Data","created":"2022-08-01","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":"2309.14771","title":"Knowledgeable In-Context Tuning: Exploring and Exploiting Factual Knowledge for In-Context Learning","created":"2023-09-26","cited_by_count":6,"area":null},{"id":"2503.05320","title":"To See a World in a Spark of Neuron: Disentangling Multi-task Interference for Training-free Model Merging","created":"2025-03-07","cited_by_count":6,"area":null},{"id":"2202.04161","title":"Logical Reasoning for Task Oriented Dialogue Systems","created":"2022-02-08","cited_by_count":5,"area":"lr"},{"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":"2502.10698","title":"Superpose Task-specific Features for Model Merging","created":"2025-02-15","cited_by_count":5,"area":null},{"id":"2309.04635","title":"Can NLP Models 'Identify', 'Distinguish', and 'Justify' Questions that Don't have a Definitive Answer?","created":"2023-09-08","cited_by_count":4,"area":null},{"id":"2505.21959","title":"EnsemW2S: Enhancing Weak-to-Strong Generalization with Large Language Model Ensembles","created":"2025-05-28","cited_by_count":4,"area":null},{"id":"2506.14126","title":"From Memorization to Parameter Interference: How Overtraining Experts Harms Model Merging","created":"2025-06-17","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":"2104.00814","title":"CURIE: An Iterative Querying Approach for Reasoning About Situations","created":"2021-04-01","cited_by_count":3,"area":null},{"id":"2107.02418","title":"Probabilistic Graph Reasoning for Natural Proof Generation","created":"2021-07-06","cited_by_count":3,"area":null},{"id":"2506.11103","title":"You Only Fine-tune Once: Many-Shot In-Context Fine-Tuning for Large Language Models","created":"2025-06-06","cited_by_count":3,"area":null},{"id":"2505.23117","title":"Decom-Renorm-Merge: Model Merging on the Right Space Improves Multitasking","created":"2025-05-29","cited_by_count":2,"area":null},{"id":"2505.23209","title":"Navigating the Accuracy-Size Trade-Off with Flexible Model Merging","created":"2025-05-29","cited_by_count":2,"area":null},{"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":"2402.14355","title":"Rule or Story, Which is a Better Commonsense Expression for Talking with Large Language Models?","created":"2024-02-22","cited_by_count":1,"area":"lr"},{"id":"2404.09717","title":"Unveiling Imitation Learning: Exploring the Impact of Data Falsity to Large Language Model","created":"2024-04-15","cited_by_count":1,"area":"offlinerl"},{"id":"2410.04571","title":"EnsemW2S: Enhancing Weak-to-Strong Generalization with Large Language Model Ensembles","created":"2024-10-06","cited_by_count":1,"area":null},{"id":"2606.22589","title":"Training-free Task Classification for Multi-Task Model Merging","created":"2026-06-21","cited_by_count":1,"area":null},{"id":"2106.02399","title":"Prediction or Comparison: Toward Interpretable Qualitative Reasoning","created":"2021-06-04","cited_by_count":0,"area":null},{"id":"2401.13907","title":"No More Distractions: an Adaptive Up-Sampling Algorithm to Reduce Data Artifacts","created":"2024-01-25","cited_by_count":0,"area":null},{"id":"2412.10416","title":"SuperMerge: An Approach For Gradient-Based Model Merging","created":"2024-12-09","cited_by_count":0,"area":null},{"id":"2503.21272","title":"Reinforced Model Merging","created":"2025-03-27","cited_by_count":0,"area":null},{"id":"2506.14040","title":"An Interdisciplinary Review of Commonsense Reasoning and Intent Detection","created":"2025-06-16","cited_by_count":0,"area":"lr"},{"id":"2508.19353","title":"Efficient Multi-Source Knowledge Transfer by Model Merging","created":"2025-08-26","cited_by_count":0,"area":null},{"id":"2509.25671","title":"The Flaw of Averages: Measuring Benchmark-Level Distributional Robustness","created":"2025-09-30","cited_by_count":0,"area":null},{"id":"2510.19988","title":"LLM-Augmented Symbolic NLU System for More Reliable Continuous Causal Statement Interpretation","created":"2025-10-22","cited_by_count":0,"area":null},{"id":"2604.01329","title":"Model Merging via Data-Free Covariance Estimation","created":"2026-04-01","cited_by_count":0,"area":null},{"id":"2604.06201","title":"Beyond Facts: Benchmarking Distributional Reading Comprehension in Large Language Models","created":"2026-03-13","cited_by_count":0,"area":null},{"id":"2606.26902","title":"Learning to Recover Task Experts from a Multi-Task Merged Model","created":"2026-06-25","cited_by_count":0,"area":null}],"next_cursor":null}