{"total":59,"rows":[{"id":"2403.07691","title":"ORPO: Monolithic Preference Optimization without Reference Model","created":"2024-03-12","cited_by_count":562,"area":"alignment"},{"id":"2206.01861","title":"ZeroQuant: Efficient and Affordable Post-Training Quantization for Large-Scale Transformers","created":"2022-06-04","cited_by_count":526,"area":null},{"id":"2310.02238","title":"Who's Harry Potter? Approximate Unlearning in LLMs","created":"2023-10-03","cited_by_count":381,"area":"safety"},{"id":"2404.19737","title":"Better & Faster Large Language Models via Multi-token Prediction","created":"2024-04-30","cited_by_count":360,"area":null},{"id":"2402.17764","title":"The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits","created":"2024-02-27","cited_by_count":308,"area":null},{"id":"2403.03329","title":"Guardrail Baselines for Unlearning in LLMs","created":"2024-03-05","cited_by_count":96,"area":"safety"},{"id":"2411.10438","title":"MARS: Unleashing the Power of Variance Reduction for Training Large Models","created":"2024-11-15","cited_by_count":64,"area":null},{"id":"2112.08688","title":"Evidentiality-guided Generation for Knowledge-Intensive NLP Tasks","created":"2021-12-16","cited_by_count":40,"area":"rag"},{"id":"2504.12285","title":"BitNet b1.58 2B4T Technical Report","created":"2025-04-16","cited_by_count":38,"area":null},{"id":"2501.06425","title":"Tensor Product Attention Is All You Need","created":"2025-01-11","cited_by_count":31,"area":null},{"id":"2406.02528","title":"Scalable MatMul-free Language Modeling","created":"2024-06-04","cited_by_count":25,"area":null},{"id":"2407.10969","title":"Q-Sparse: All Large Language Models can be Fully Sparsely-Activated","created":"2024-07-15","cited_by_count":25,"area":null},{"id":"2501.14851","title":"JustLogic: A Comprehensive Benchmark for Evaluating Deductive Reasoning in Large Language Models","created":"2025-01-24","cited_by_count":22,"area":"lr"},{"id":"2402.17355","title":"RECOST: External Knowledge Guided Data-efficient Instruction Tuning","created":"2024-02-27","cited_by_count":18,"area":null},{"id":"2504.18415","title":"BitNet v2: Native 4-bit Activations with Hadamard Transformation for 1-bit LLMs","created":"2025-04-25","cited_by_count":18,"area":null},{"id":"2105.11776","title":"Dynamic Semantic Graph Construction and Reasoning for Explainable Multi-hop Science Question Answering","created":"2021-05-25","cited_by_count":17,"area":null},{"id":"2205.02593","title":"METGEN: A Module-Based Entailment Tree Generation Framework for Answer Explanation","created":"2022-05-05","cited_by_count":17,"area":"lr"},{"id":"2209.07662","title":"NELLIE: A Neuro-Symbolic Inference Engine for Grounded, Compositional, and Explainable Reasoning","created":"2022-09-16","cited_by_count":16,"area":"lr"},{"id":"2109.02905","title":"Exploiting Reasoning Chains for Multi-hop Science Question Answering","created":"2021-09-07","cited_by_count":15,"area":null},{"id":"2405.17484","title":"Bridging The Gap between Low-rank and Orthogonal Adaptation via Householder Reflection Adaptation","created":"2024-05-24","cited_by_count":15,"area":null},{"id":"2212.03597","title":"DeepSpeed Data Efficiency: Improving Deep Learning Model Quality and Training Efficiency via Efficient Data Sampling and Routing","created":"2022-12-07","cited_by_count":13,"area":null},{"id":"2505.13893","title":"InfiGFusion: Graph-on-Logits Distillation via Efficient Gromov-Wasserstein for Model Fusion","created":"2025-05-20","cited_by_count":12,"area":null},{"id":"2211.11586","title":"Random-LTD: Random and Layerwise Token Dropping Brings Efficient Training for Large-scale Transformers","created":"2022-11-17","cited_by_count":11,"area":null},{"id":"2407.11722","title":"Exploring Quantization for Efficient Pre-Training of Transformer Language Models","created":"2024-07-16","cited_by_count":10,"area":null},{"id":"2502.15435","title":"Single-pass Detection of Jailbreaking Input in Large Language Models","created":"2025-02-21","cited_by_count":10,"area":"alignment"},{"id":"2505.21487","title":"Hardware-Efficient Attention for Fast Decoding","created":"2025-05-27","cited_by_count":10,"area":"inference"},{"id":"2510.21800","title":"MARS-M: When Variance Reduction Meets Matrices","created":"2025-10-20","cited_by_count":10,"area":null},{"id":"2601.00417","title":"Deep Delta Learning","created":"2026-01-01","cited_by_count":9,"area":null},{"id":"2505.13878","title":"InfiFPO: Implicit Model Fusion via Preference Optimization in Large Language Models","created":"2025-05-20","cited_by_count":8,"area":"alignment"},{"id":"2505.24275","title":"GradPower: Powering Gradients for Faster Language Model Pre-Training","created":"2025-05-30","cited_by_count":8,"area":null},{"id":"2105.03417","title":"Diff-Explainer: Differentiable Convex Optimization for Explainable Multi-hop Inference","created":"2021-05-07","cited_by_count":7,"area":null},{"id":"2412.01020","title":"AI Benchmarks and Datasets for LLM Evaluation","created":"2024-12-02","cited_by_count":7,"area":null},{"id":"2502.11034","title":"AdaGC: Enhancing LLM Pretraining Stability via Adaptive Gradient Clipping","created":"2025-02-16","cited_by_count":6,"area":null},{"id":"2509.13765","title":"TENET: An Efficient Sparsity-Aware LUT-Centric Architecture for Ternary LLM Inference On Edge","created":"2025-09-17","cited_by_count":6,"area":null},{"id":"2305.14237","title":"HOP, UNION, GENERATE: Explainable Multi-hop Reasoning without Rationale Supervision","created":"2023-05-23","cited_by_count":5,"area":"lr"},{"id":"2501.02795","title":"InfiFusion: A Unified Framework for Enhanced Cross-Model Reasoning via LLM Fusion","created":"2025-01-06","cited_by_count":5,"area":"lr"},{"id":"2508.05571","title":"iFairy: the First 2-bit Complex LLM with All Parameters in $\\{\\pm1, \\pm i\\}$","created":"2025-08-07","cited_by_count":5,"area":null},{"id":"2509.19358","title":"Benchmarking and Improving LLM Robustness for Personalized Generation","created":"2025-09-18","cited_by_count":4,"area":null},{"id":"2105.05737","title":"Encoding Explanatory Knowledge for Zero-shot Science Question Answering","created":"2021-05-12","cited_by_count":3,"area":null},{"id":"2210.13432","title":"Towards Better Few-Shot and Finetuning Performance with Forgetful Causal Language Models","created":"2022-10-24","cited_by_count":3,"area":null},{"id":"2210.14606","title":"Analyzing Multi-Task Learning for Abstractive Text Summarization","created":"2022-10-26","cited_by_count":3,"area":null},{"id":"2403.06410","title":"A Logical Pattern Memory Pre-trained Model for Entailment Tree Generation","created":"2024-03-11","cited_by_count":3,"area":null},{"id":"2404.02684","title":"Cross-Architecture Transfer Learning for Linear-Cost Inference Transformers","created":"2024-04-03","cited_by_count":3,"area":null},{"id":"2605.26647","title":"More Expressive Feedforward Layers: Part I. Token-Adaptive Mixing of Activations","created":"2026-05-26","cited_by_count":3,"area":null},{"id":"2302.01806","title":"Mitigating Data Scarcity for Large Language Models","created":"2023-02-03","cited_by_count":2,"area":null},{"id":"2406.17990","title":"Explicit Diversity Conditions for Effective Question Answer Generation with Large Language Models","created":"2024-06-26","cited_by_count":2,"area":null},{"id":"2412.01042","title":"TruncFormer: Private LLM Inference Using Only Truncations","created":"2024-12-02","cited_by_count":2,"area":null},{"id":"2512.02901","title":"Fairy2i: Training Complex LLMs from Real LLMs with All Parameters in $\\{\\pm 1, \\pm i\\}$","created":"2025-12-02","cited_by_count":2,"area":null},{"id":"2601.07212","title":"MI-PRUN: Optimize Large Language Model Pruning via Mutual Information","created":"2026-01-12","cited_by_count":2,"area":null},{"id":"2603.02188","title":"Multi-Head Low-Rank Attention","created":"2026-03-02","cited_by_count":2,"area":"inference"},{"id":"2208.03339","title":"Going Beyond Approximation: Encoding Constraints for Explainable Multi-hop Inference via Differentiable Combinatorial Solvers","created":"2022-08-05","cited_by_count":1,"area":null},{"id":"2404.02625","title":"A Differentiable Integer Linear Programming Solver for Explanation-Based Natural Language Inference","created":"2024-04-03","cited_by_count":1,"area":null},{"id":"2506.23146","title":"Learning-to-Context Slope: Evaluating In-Context Learning Effectiveness Beyond Performance Illusions","created":"2025-06-29","cited_by_count":1,"area":null},{"id":"2508.00385","title":"Multi-Layer Attention is the Amplifier of Demonstration Effectiveness","created":"2025-08-01","cited_by_count":1,"area":null},{"id":"2112.09423","title":"ActKnow: Active External Knowledge Infusion Learning for Question Answering in Low Data Regime","created":"2021-12-17","cited_by_count":0,"area":null},{"id":"2509.07301","title":"Causal Attention with Lookahead Keys","created":"2025-09-09","cited_by_count":0,"area":null},{"id":"2602.22592","title":"pQuant: Towards Effective Low-Bit Language Models via Decoupled Linear Quantization-Aware Training","created":"2026-02-26","cited_by_count":0,"area":null},{"id":"2607.16227","title":"LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats","created":"2026-06-23","cited_by_count":0,"area":"safety"},{"id":"2608.30439","title":"Event-Driven Language Models with Sparse Neural Activity for Neuromorphic Hardware","created":"2026-08-31","cited_by_count":0,"area":"inference"}],"next_cursor":null}