{"total":35,"rows":[{"id":"2410.16251","title":"Can Knowledge Editing Really Correct Hallucinations?","created":"2024-10-21","cited_by_count":28,"area":null},{"id":"2410.00593","title":"Style-Specific Neurons for Steering LLMs in Text Style Transfer","created":"2024-10-01","cited_by_count":24,"area":null},{"id":"2405.06800","title":"LLM-Generated Black-box Explanations Can Be Adversarially Helpful","created":"2024-05-10","cited_by_count":21,"area":null},{"id":"2410.07054","title":"Mitigating the Language Mismatch and Repetition Issues in LLM-based Machine Translation via Model Editing","created":"2024-10-09","cited_by_count":18,"area":null},{"id":"2502.14258","title":"Does Time Have Its Place? Temporal Heads: Where Language Models Recall Time-specific Information","created":"2025-02-20","cited_by_count":15,"area":null},{"id":"2405.02765","title":"Has this Fact been Edited? Detecting Knowledge Edits in Language Models","created":"2024-05-04","cited_by_count":14,"area":null},{"id":"2407.03779","title":"Sheaf Discovery with Joint Computation Graph Pruning and Flexible Granularity","created":"2024-07-04","cited_by_count":14,"area":null},{"id":"2405.14117","title":"Knowledge Localization: Mission Not Accomplished? Enter Query Localization!","created":"2024-05-23","cited_by_count":13,"area":null},{"id":"2505.20154","title":"UORA: Uniform Orthogonal Reinitialization Adaptation in Parameter-Efficient Fine-Tuning of Large Models","created":"2025-05-26","cited_by_count":11,"area":null},{"id":"2410.10796","title":"Context-Parametric Inversion: Why Instruction Finetuning Can Worsen Context Reliance","created":"2024-10-14","cited_by_count":10,"area":null},{"id":"2405.05966","title":"Natural Language Processing RELIES on Linguistics","created":"2024-05-09","cited_by_count":9,"area":null},{"id":"2408.04965","title":"Generalisation First, Memorisation Second? Memorisation Localisation for Natural Language Classification Tasks","created":"2024-08-09","cited_by_count":9,"area":null},{"id":"2505.09338","title":"Llama See, Llama Do: A Mechanistic Perspective on Contextual Entrainment and Distraction in LLMs","created":"2025-05-14","cited_by_count":6,"area":null},{"id":"2506.00829","title":"COMPKE: Complex Question Answering under Knowledge Editing","created":"2025-06-01","cited_by_count":6,"area":null},{"id":"2502.20408","title":"Brain-Inspired Exploration of Functional Networks and Key Neurons in Large Language Models","created":"2025-02-13","cited_by_count":5,"area":null},{"id":"2406.17253","title":"How Well Can Knowledge Edit Methods Edit Perplexing Knowledge?","created":"2024-06-25","cited_by_count":4,"area":null},{"id":"2505.24788","title":"Drop Dropout on Single-Epoch Language Model Pretraining","created":"2025-05-30","cited_by_count":4,"area":null},{"id":"2506.10641","title":"Spelling-out is not Straightforward: LLMs' Capability of Tokenization from Token to Characters","created":"2025-06-12","cited_by_count":4,"area":null},{"id":"2511.12991","title":"Fine-Tuned LLMs Know They Don't Know: A Parameter-Efficient Approach to Recovering Honesty","created":"2025-11-17","cited_by_count":3,"area":null},{"id":"2406.17241","title":"Understanding Language Model Circuits through Knowledge Editing","created":"2024-06-25","cited_by_count":2,"area":null},{"id":"2505.12182","title":"Truth Neurons","created":"2025-05-18","cited_by_count":2,"area":null},{"id":"2604.05688","title":"Attention Editing: A Versatile Framework for Cross-Architecture Attention Conversion","created":"2026-04-07","cited_by_count":2,"area":null},{"id":"2505.16178","title":"Understanding Fact Recall in Language Models: Why Two-Stage Training Encourages Memorization but Mixed Training Teaches Knowledge","created":"2025-05-22","cited_by_count":1,"area":null},{"id":"2505.17936","title":"Understanding Gated Neurons in Transformers from Their Input-Output Functionality","created":"2025-05-23","cited_by_count":1,"area":null},{"id":"2510.09421","title":"On the Representations of Entities in Auto-regressive Large Language Models","created":"2025-10-10","cited_by_count":1,"area":null},{"id":"2510.19036","title":"From Memorization to Generalization: Fine-Tuning Large Language Models for Biomedical Term-to-Identifier Normalization","created":"2025-10-21","cited_by_count":1,"area":null},{"id":"2504.04997","title":"SurvSurf: a partially monotonic neural network for first-hitting time prediction of intermittently observed discrete and continuous sequential events","created":"2025-04-07","cited_by_count":0,"area":null},{"id":"2510.12115","title":"Tracing Multilingual Knowledge Acquisition Dynamics in Domain Adaptation: A Case Study of English-Japanese Biomedical Adaptation","created":"2025-10-14","cited_by_count":0,"area":null},{"id":"2601.21864","title":"Knowing Bias, Doing Better: Mitigating Social Bias in LLMs via Know-Bias Neuron Enhancement","created":"2026-01-29","cited_by_count":0,"area":null},{"id":"2602.05694","title":"Consensus-Aligned Neuron Efficient Fine-Tuning Large Language Models for Multi-Domain Machine Translation","created":"2026-02-05","cited_by_count":0,"area":null},{"id":"2602.23826","title":"GLUScope: A Tool for Analyzing GLU Neurons in Transformer Language Models","created":"2026-02-27","cited_by_count":0,"area":null},{"id":"2605.12299","title":"GKnow: Measuring the Entanglement of Gender Bias and Factual Gender","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2607.11193","title":"RepTran: Search-Based Repair of Transformer Models","created":"2026-07-13","cited_by_count":0,"area":null},{"id":"2609.05743","title":"Some Tokens Behave like Magnets: Revealing Linguistic Organization in the Layers of Language Models","created":"2026-09-04","cited_by_count":0,"area":null},{"id":"2609.18612","title":"Weakening Neurons: An Input-Output Functionality in Transformers with Outsize Influence","created":"2026-09-16","cited_by_count":0,"area":null}],"next_cursor":null}