{"list":"other","total":99,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2101.03961","title":"Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity","created":"2021-01-11","cited_by_count":3073},{"id":"2109.07958","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","created":"2021-09-08","cited_by_count":2975},{"id":"1705.03551","title":"TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension","created":"2017-05-09","cited_by_count":2955},{"id":"1509.01626","title":"Character-level Convolutional Networks for Text Classification","created":"2015-09-04","cited_by_count":2330},{"id":"2002.05202","title":"GLU Variants Improve Transformer","created":"2020-02-12","cited_by_count":1804},{"id":"2012.14913","title":"Transformer Feed-Forward Layers Are Key-Value Memories","created":"2020-12-29","cited_by_count":1336},{"id":"1808.08745","title":"Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization","created":"2018-08-27","cited_by_count":1317},{"id":"2306.03341","title":"Inference-Time Intervention: Eliciting Truthful Answers from a Language Model","created":"2023-06-06","cited_by_count":1302},{"id":"2211.00593","title":"Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small","created":"2022-11-01","cited_by_count":1165},{"id":"2209.11895","title":"In-context Learning and Induction Heads","created":"2022-09-24","cited_by_count":964},{"id":"2002.04745","title":"On Layer Normalization in the Transformer Architecture","created":"2020-02-12","cited_by_count":922},{"id":"1905.09418","title":"Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned","created":"2019-05-23","cited_by_count":856},{"id":"2304.14997","title":"Towards Automated Circuit Discovery for Mechanistic Interpretability","created":"2023-04-28","cited_by_count":724},{"id":"2311.03658","title":"The Linear Representation Hypothesis and the Geometry of Large Language Models","created":"2023-11-07","cited_by_count":716},{"id":"2104.08696","title":"Knowledge Neurons in Pretrained Transformers","created":"2021-04-18","cited_by_count":601},{"id":"2304.14767","title":"Dissecting Recall of Factual Associations in Auto-Regressive Language Models","created":"2023-04-28","cited_by_count":528},{"id":"1806.00069","title":"Explaining Explanations: An Overview of Interpretability of Machine Learning","created":"2018-05-31","cited_by_count":508},{"id":"2106.02997","title":"Causal Abstractions of Neural Networks","created":"2021-06-06","cited_by_count":422},{"id":"2309.16042","title":"Towards Best Practices of Activation Patching in Language Models: Metrics and Methods","created":"2023-09-27","cited_by_count":359},{"id":"1706.07979","title":"Methods for Interpreting and Understanding Deep Neural Networks","created":"2017-06-24","cited_by_count":345},{"id":"2310.15213","title":"Function Vectors in Large Language Models","created":"2023-10-23","cited_by_count":308},{"id":"1908.08593","title":"Revealing the Dark Secrets of BERT","created":"2019-08-21","cited_by_count":301},{"id":"2305.14795","title":"MQuAKE: Assessing Knowledge Editing in Language Models via Multi-Hop Questions","created":"2023-05-24","cited_by_count":300},{"id":"2407.06204","title":"A Survey on Mixture of Experts in Large Language Models","created":"2024-06-26","cited_by_count":237},{"id":"2404.15574","title":"Retrieval Head Mechanistically Explains Long-Context Factuality","created":"2024-04-24","cited_by_count":232},{"id":"2010.15875","title":"Retrieve, Program, Repeat: Complex Knowledge Base Question Answering via Alternate Meta-learning","created":"2020-10-29","cited_by_count":216},{"id":"2404.15255","title":"How to use and interpret activation patching","created":"2024-04-23","cited_by_count":214},{"id":"2004.08249","title":"Understanding the Difficulty of Training Transformers","created":"2020-04-17","cited_by_count":210},{"id":"2303.02536","title":"Finding Alignments Between Interpretable Causal Variables and Distributed Neural Representations","created":"2023-03-05","cited_by_count":209},{"id":"2305.00586","title":"How does GPT-2 compute greater-than?: Interpreting mathematical abilities in a pre-trained language model","created":"2023-04-30","cited_by_count":202},{"id":"2308.09124","title":"Linearity of Relation Decoding in Transformer Language Models","created":"2023-08-17","cited_by_count":200},{"id":"1902.04094","title":"BERT has a Mouth, and It Must Speak: BERT as a Markov Random Field Language Model","created":"2019-02-11","cited_by_count":185},{"id":"2207.07051","title":"Language models show human-like content effects on reasoning tasks","created":"2022-07-14","cited_by_count":173},{"id":"2310.15154","title":"Linear Representations of Sentiment in Large Language Models","created":"2023-10-23","cited_by_count":163},{"id":"2306.00802","title":"Birth of a Transformer: A Memory Viewpoint","created":"2023-06-01","cited_by_count":161},{"id":"1909.00015","title":"Adaptively Sparse Transformers","created":"2019-08-30","cited_by_count":155},{"id":"2305.09731","title":"What In-Context Learning \"Learns\" In-Context: Disentangling Task Recognition and Task Learning","created":"2023-05-16","cited_by_count":152},{"id":"2307.09458","title":"Does Circuit Analysis Interpretability Scale? Evidence from Multiple Choice Capabilities in Chinchilla","created":"2023-07-18","cited_by_count":149},{"id":"2407.07071","title":"Lookback Lens: Detecting and Mitigating Contextual Hallucinations in Large Language Models Using Only Attention Maps","created":"2024-07-09","cited_by_count":142},{"id":"2207.13243","title":"Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networks","created":"2022-07-27","cited_by_count":129},{"id":"1904.02874","title":"An Attentive Survey of Attention Models","created":"2019-04-05","cited_by_count":124},{"id":"2309.07311","title":"Sudden Drops in the Loss: Syntax Acquisition, Phase Transitions, and Simplicity Bias in MLMs","created":"2023-09-13","cited_by_count":124},{"id":"1904.02342","title":"Text Generation from Knowledge Graphs with Graph Transformers","created":"2019-04-04","cited_by_count":122},{"id":"2312.03002","title":"The mechanistic basis of data dependence and abrupt learning in an in-context classification task","created":"2023-12-03","cited_by_count":118},{"id":"2402.11004","title":"The Evolution of Statistical Induction Heads: In-Context Learning Markov Chains","created":"2024-02-16","cited_by_count":118},{"id":"2310.08744","title":"Circuit Component Reuse Across Tasks in Transformer Language Models","created":"2023-10-12","cited_by_count":108},{"id":"2407.15891","title":"RazorAttention: Efficient KV Cache Compression Through Retrieval Heads","created":"2024-07-22","cited_by_count":100},{"id":"2403.00824","title":"Information Flow Routes: Automatically Interpreting Language Models at Scale","created":"2024-02-27","cited_by_count":95},{"id":"2312.14033","title":"T-Eval: Evaluating the Tool Utilization Capability of Large Language Models Step by Step","created":"2023-12-21","cited_by_count":93},{"id":"2109.07684","title":"Language Models are Few-shot Multilingual Learners","created":"2021-09-16","cited_by_count":92},{"id":"2402.18154","title":"Cutting Off the Head Ends the Conflict: A Mechanism for Interpreting and Mitigating Knowledge Conflicts in Language Models","created":"2024-02-28","cited_by_count":91},{"id":"2305.15054","title":"A Mechanistic Interpretation of Arithmetic Reasoning in Language Models using Causal Mediation Analysis","created":"2023-05-24","cited_by_count":89},{"id":"2401.12973","title":"In-Context Language Learning: Architectures and Algorithms","created":"2024-01-23","cited_by_count":89},{"id":"2404.07129","title":"What needs to go right for an induction head? A mechanistic study of in-context learning circuits and their formation","created":"2024-04-10","cited_by_count":89},{"id":"2309.04827","title":"Neurons in Large Language Models: Dead, N-gram, Positional","created":"2023-09-09","cited_by_count":88},{"id":"2407.03282","title":"LLM Internal States Reveal Hallucination Risk Faced With a Query","created":"2024-07-03","cited_by_count":82},{"id":"2107.12979","title":"Predictive Coding: a Theoretical and Experimental Review","created":"2021-07-27","cited_by_count":77},{"id":"2312.09230","title":"Successor Heads: Recurring, Interpretable Attention Heads In The Wild","created":"2023-12-14","cited_by_count":77},{"id":"2310.04625","title":"Copy Suppression: Comprehensively Understanding an Attention Head","created":"2023-10-06","cited_by_count":76},{"id":"2203.14263","title":"A General Survey on Attention Mechanisms in Deep Learning","created":"2022-03-27","cited_by_count":64},{"id":"2405.17969","title":"Knowledge Circuits in Pretrained Transformers","created":"2024-05-28","cited_by_count":60},{"id":"2406.01563","title":"LoFiT: Localized Fine-tuning on LLM Representations","created":"2024-06-03","cited_by_count":57},{"id":"2408.12599","title":"Controllable Text Generation for Large Language Models: A Survey","created":"2024-08-22","cited_by_count":57},{"id":"2407.14507","title":"Internal Consistency and Self-Feedback in Large Language Models: A Survey","created":"2024-07-19","cited_by_count":50},{"id":"2302.01308","title":"Large language models predict human sensory judgments across six modalities","created":"2023-02-02","cited_by_count":48},{"id":"2401.12874","title":"From Understanding to Utilization: A Survey on Explainability for Large Language Models","created":"2024-01-23","cited_by_count":48},{"id":"2402.13055","title":"Identifying Semantic Induction Heads to Understand In-Context Learning","created":"2024-02-20","cited_by_count":47},{"id":"2407.07011","title":"Induction Heads as an Essential Mechanism for Pattern Matching in In-context Learning","created":"2024-07-09","cited_by_count":46},{"id":"2406.14909","title":"Mixture of Attention Spans: Optimizing LLM Inference Efficiency with Heterogeneous Sliding-Window Lengths","created":"2024-06-21","cited_by_count":44},{"id":"2301.12971","title":"Quantifying Context Mixing in Transformers","created":"2023-01-30","cited_by_count":43},{"id":"2402.07321","title":"Summing Up the Facts: Additive Mechanisms Behind Factual Recall in LLMs","created":"2024-02-11","cited_by_count":42},{"id":"2402.11655","title":"Competition of Mechanisms: Tracing How Language Models Handle Facts and Counterfactuals","created":"2024-02-18","cited_by_count":40},{"id":"2401.17671","title":"Contextual Feature Extraction Hierarchies Converge in Large Language Models and the Brain","created":"2024-01-31","cited_by_count":32},{"id":"2403.19521","title":"Interpreting Key Mechanisms of Factual Recall in Transformer-Based Language Models","created":"2024-03-28","cited_by_count":31},{"id":"2406.02128","title":"Iteration Head: A Mechanistic Study of Chain-of-Thought","created":"2024-06-04","cited_by_count":31},{"id":"2408.08590","title":"Reasoning Circuits in Language Models: A Mechanistic Interpretation of Syllogistic Inference","created":"2024-08-16","cited_by_count":29},{"id":"2402.02872","title":"How do Large Language Models Learn In-Context? Query and Key Matrices of In-Context Heads are Two Towers for Metric Learning","created":"2024-02-05","cited_by_count":18},{"id":"2101.09115","title":"The heads hypothesis: A unifying statistical approach towards understanding multi-headed attention in BERT","created":"2021-01-22","cited_by_count":15},{"id":"2204.12406","title":"A survey on attention mechanisms for medical applications: are we moving towards better algorithms?","created":"2022-04-26","cited_by_count":15},{"id":"2405.14992","title":"Linking In-context Learning in Transformers to Human Episodic Memory","created":"2024-05-23","cited_by_count":15},{"id":"2405.04156","title":"How does GPT-2 Predict Acronyms? Extracting and Understanding a Circuit via Mechanistic Interpretability","created":"2024-05-07","cited_by_count":14},{"id":"2407.19842","title":"Detecting and Understanding Vulnerabilities in Language Models via Mechanistic Interpretability","created":"2024-07-29","cited_by_count":13},{"id":"2201.09305","title":"An Analysis and Comparison of ACT-R and Soar","created":"2022-01-23","cited_by_count":12},{"id":"2311.03839","title":"Aspects of human memory and Large Language Models","created":"2023-11-07","cited_by_count":12},{"id":"2408.00137","title":"Correcting Negative Bias in Large Language Models through Negative Attention Score Alignment","created":"2024-07-31","cited_by_count":12},{"id":"2407.10153","title":"Look Within, Why LLMs Hallucinate: A Causal Perspective","created":"2024-07-14","cited_by_count":11},{"id":"2112.05909","title":"Neural Attention Models in Deep Learning: Survey and Taxonomy","created":"2021-12-11","cited_by_count":8},{"id":"2403.00862","title":"NewsBench: A Systematic Evaluation Framework for Assessing Editorial Capabilities of Large Language Models in Chinese Journalism","created":"2024-02-29","cited_by_count":8},{"id":"1306.0125","title":"Understanding ACT-R - an Outsider's Perspective","created":"2013-06-01","cited_by_count":4},{"id":"2405.03340","title":"Functional Equivalence with NARS","created":"2024-05-06","cited_by_count":2}],"next_cursor":null}