{"total":48,"rows":[{"id":"2109.07958","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","created":"2021-09-08","cited_by_count":2975,"area":null},{"id":"2404.05892","title":"Eagle and Finch: RWKV with Matrix-Valued States and Dynamic Recurrence","created":"2024-04-08","cited_by_count":159,"area":null},{"id":"2303.08518","title":"UPRISE: Universal Prompt Retrieval for Improving Zero-Shot Evaluation","created":"2023-03-15","cited_by_count":75,"area":null},{"id":"2403.17752","title":"Can multiple-choice questions really be useful in detecting the abilities of LLMs?","created":"2024-03-26","cited_by_count":69,"area":null},{"id":"2307.07164","title":"Learning to Retrieve In-Context Examples for Large Language Models","created":"2023-07-14","cited_by_count":60,"area":null},{"id":"2409.03137","title":"The AdEMAMix Optimizer: Better, Faster, Older","created":"2024-09-05","cited_by_count":54,"area":null},{"id":"2104.08727","title":"GooAQ: Open Question Answering with Diverse Answer Types","created":"2021-04-18","cited_by_count":53,"area":null},{"id":"2502.14127","title":"Which of These Best Describes Multiple Choice Evaluation with LLMs? A) Forced B) Flawed C) Fixable D) All of the Above","created":"2025-02-19","cited_by_count":52,"area":null},{"id":"2309.09530","title":"Adapting Large Language Models to Domains via Reading Comprehension","created":"2023-09-18","cited_by_count":50,"area":null},{"id":"2307.02394","title":"Won't Get Fooled Again: Answering Questions with False Premises","created":"2023-07-05","cited_by_count":48,"area":null},{"id":"2109.02593","title":"General-Purpose Question-Answering with Macaw","created":"2021-09-06","cited_by_count":40,"area":null},{"id":"2407.07064","title":"Prompting Techniques for Secure Code Generation: A Systematic Investigation","created":"2024-07-09","cited_by_count":34,"area":null},{"id":"2502.17282","title":"Capability Instruction Tuning: A New Paradigm for Dynamic LLM Routing","created":"2025-02-24","cited_by_count":25,"area":null},{"id":"2410.07959","title":"COMPL-AI Framework: A Technical Interpretation and LLM Benchmarking Suite for the EU Artificial Intelligence Act","created":"2024-10-10","cited_by_count":24,"area":null},{"id":"2112.10006","title":"Zero-shot and Few-shot Learning with Knowledge Graphs: A Comprehensive Survey","created":"2021-12-18","cited_by_count":23,"area":null},{"id":"2507.17634","title":"WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training","created":"2025-07-23","cited_by_count":23,"area":null},{"id":"2406.10421","title":"SciEx: Benchmarking Large Language Models on Scientific Exams with Human Expert Grading and Automatic Grading","created":"2024-06-14","cited_by_count":14,"area":null},{"id":"2502.14502","title":"How Much Knowledge Can You Pack into a LoRA Adapter without Harming LLM?","created":"2025-02-20","cited_by_count":13,"area":null},{"id":"2410.18808","title":"Delving into the Reversal Curse: How Far Can Large Language Models Generalize?","created":"2024-10-24","cited_by_count":11,"area":null},{"id":"2402.15414","title":"Does Combining Parameter-efficient Modules Improve Few-shot Transfer Accuracy?","created":"2024-02-23","cited_by_count":9,"area":null},{"id":"2205.00395","title":"ELQA: A Corpus of Metalinguistic Questions and Answers about English","created":"2022-05-01","cited_by_count":8,"area":null},{"id":"2402.13874","title":"$Se^2$: Sequential Example Selection for In-Context Learning","created":"2024-02-21","cited_by_count":8,"area":null},{"id":"2310.10920","title":"NuclearQA: A Human-Made Benchmark for Language Models for the Nuclear Domain","created":"2023-10-17","cited_by_count":7,"area":null},{"id":"2402.17812","title":"DropBP: Accelerating Fine-Tuning of Large Language Models by Dropping Backward Propagation","created":"2024-02-27","cited_by_count":7,"area":null},{"id":"2407.10804","title":"Mix-CPT: A Domain Adaptation Framework via Decoupling Knowledge Learning and Format Alignment","created":"2024-07-15","cited_by_count":7,"area":null},{"id":"2508.15390","title":"Exploiting Vocabulary Frequency Imbalance in Language Model Pre-training","created":"2025-08-21","cited_by_count":7,"area":null},{"id":"2601.17858","title":"MergeMix: Optimizing Mid-Training Data Mixtures via Learnable Model Merging","created":"2026-01-25","cited_by_count":7,"area":null},{"id":"2403.17552","title":"Naive Bayes-based Context Extension for Large Language Models","created":"2024-03-26","cited_by_count":5,"area":null},{"id":"2512.23422","title":"Entropy-Guided Token Dropout: Training Autoregressive Language Models with Limited Domain Data","created":"2025-12-29","cited_by_count":5,"area":null},{"id":"2606.10650","title":"Dynamic Linear Attention","created":"2026-06-09","cited_by_count":5,"area":null},{"id":"2104.08401","title":"Enriching a Model's Notion of Belief using a Persistent Memory","created":"2021-04-16","cited_by_count":4,"area":null},{"id":"2301.13089","title":"Can an AI Win Ghana's National Science and Maths Quiz? An AI Grand Challenge for Education","created":"2023-01-30","cited_by_count":4,"area":null},{"id":"2603.03597","title":"NuMuon: Nuclear-Norm-Constrained Muon for Compressible LLM Training","created":"2026-03-04","cited_by_count":4,"area":null},{"id":"2408.15600","title":"Exploring Selective Layer Fine-Tuning in Federated Learning","created":"2024-08-28","cited_by_count":3,"area":null},{"id":"2511.23319","title":"Every Token Counts: Generalizing 16M Ultra-Long Context in Large Language Models","created":"2025-11-28","cited_by_count":3,"area":null},{"id":"2308.00946","title":"Teaching Smaller Language Models To Generalise To Unseen Compositional Questions","created":"2023-08-02","cited_by_count":2,"area":null},{"id":"2409.20385","title":"Wait, but Tylenol is Acetaminophen... Investigating and Improving Language Models' Ability to Resist Requests for Misinformation","created":"2024-09-30","cited_by_count":2,"area":null},{"id":"2505.14070","title":"Enhancing LLMs via High-Knowledge Data Selection","created":"2025-05-20","cited_by_count":2,"area":null},{"id":"2512.00290","title":"EduEval: A Hierarchical Cognitive Benchmark for Evaluating Large Language Models in Chinese Education","created":"2025-11-29","cited_by_count":2,"area":null},{"id":"2510.23052","title":"Knocking-Heads Attention","created":"2025-10-27","cited_by_count":1,"area":null},{"id":"2605.22205","title":"Skill Weaving: Efficient LLM Improvement via Modular Skillpacks","created":"2026-05-21","cited_by_count":1,"area":null},{"id":"2606.28057","title":"MultiHashFormer: Hash-based Generative Language Models","created":"2026-06-26","cited_by_count":1,"area":null},{"id":"2608.06539","title":"Don't `Well, Actually' Me Unless You Know What You're Talking About: Weak Presupposition Verification Degrades General QA Performance","created":"2026-08-06","cited_by_count":1,"area":null},{"id":"2409.20181","title":"Reference Trustable Decoding: A Training-Free Augmentation Paradigm for Large Language Models","created":"2024-09-30","cited_by_count":0,"area":null},{"id":"2411.16985","title":"Teaching Smaller Language Models To Generalise To Unseen Compositional Questions (Full Thesis)","created":"2024-11-25","cited_by_count":0,"area":null},{"id":"2601.07430","title":"KALE: Enhancing Knowledge Manipulation in Large Language Models via Knowledge-aware Learning","created":"2026-01-12","cited_by_count":0,"area":null},{"id":"2609.24417","title":"ARM: Attention with Routed-Memory for Learnable Sparse Control","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2610.04399","title":"GlitchPatch: Repairing Glitch Tokens in Frozen Language Models via Local Retokenization","created":"2026-10-03","cited_by_count":0,"area":null}],"next_cursor":null}