Image de couverture de livre

Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity Tracking

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Prakash, Nikhil, Shaham, Tamar Rott, Haklay, Tal, Belinkov, Yonatan, Bau, David
Format:	Preprint
Publié:	2024
Sujets:	Computation and Language Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Position-aware Automatic Circuit Discovery
par: Haklay, Tal, et autres
Publié: (2025)

Language Models use Lookbacks to Track Beliefs
par: Prakash, Nikhil, et autres
Publié: (2025)

The Dual Mechanisms of Spatial Reasoning in Vision-Language Models
par: Cui, Kelly, et autres
Publié: (2026)

Planted in Pretraining, Swayed by Finetuning: A Case Study on the Origins of Cognitive Biases in LLMs
par: Itzhak, Itay, et autres
Publié: (2025)

Pitfalls in Evaluating Interpretability Agents
par: Haklay, Tal, et autres
Publié: (2026)

Linearity of Relation Decoding in Transformer Language Models
par: Hernandez, Evan, et autres
Publié: (2023)

Have Faith in Faithfulness: Going Beyond Circuit Overlap When Finding Model Mechanisms
par: Hanna, Michael, et autres
Publié: (2024)

Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models
par: Marks, Samuel, et autres
Publié: (2024)

PRISM: PRIor from corpus Statistics for topic Modeling
par: Ishon, Tal, et autres
Publié: (2026)

Leveraging Prototypical Representations for Mitigating Social Bias without Demographic Information
par: Iskander, Shadi, et autres
Publié: (2024)

SAEs Are Good for Steering -- If You Select the Right Features
par: Arad, Dana, et autres
Publié: (2025)

MIB: A Mechanistic Interpretability Benchmark
par: Mueller, Aaron, et autres
Publié: (2025)

Fast Forwarding Low-Rank Training
par: Rahamim, Adir, et autres
Publié: (2024)

Silent Tokens, Loud Effects: Padding in LLMs
par: Himelstein, Rom, et autres
Publié: (2025)

A Vision Check-up for Language Models
par: Sharma, Pratyusha, et autres
Publié: (2024)

Backward Lens: Projecting Language Model Gradients into the Vocabulary Space
par: Katz, Shahar, et autres
Publié: (2024)

From Feelings to Metrics: Understanding and Formalizing How Users Vibe-Test LLMs
par: Itzhak, Itay, et autres
Publié: (2026)

Unified Concept Editing in Diffusion Models
par: Gandikota, Rohit, et autres
Publié: (2023)

Ranking Entities along Conceptual Space Dimensions with LLMs: An Analysis of Fine-Tuning Strategies
par: Kumar, Nitesh, et autres
Publié: (2024)

Tracking Universal Features Through Fine-Tuning and Model Merging
par: Horn, Niels, et autres
Publié: (2024)

Safety Subspaces are Not Linearly Distinct: A Fine-Tuning Case Study
par: Ponkshe, Kaustubh, et autres
Publié: (2025)

Bridging the Visual Gap: Fine-Tuning Multimodal Models with Knowledge-Adapted Captions
par: Yanuka, Moran, et autres
Publié: (2024)

Slot Machines: How LLMs Keep Track of Multiple Entities
par: Bogdan, Paul C., et autres
Publié: (2026)

Large Language Models Generate Harmful Content Using a Distinct, Unified Mechanism
par: Orgad, Hadas, et autres
Publié: (2026)

Entity-Centric Reinforcement Learning for Object Manipulation from Pixels
par: Haramati, Dan, et autres
Publié: (2024)

Mechanisms of AI Protein Folding in ESMFold
par: Lu, Kevin, et autres
Publié: (2026)

Enhancing BERT Fine-Tuning for Sentiment Analysis in Lower-Resourced Languages
par: Kubík, Jozef, et autres
Publié: (2025)

Confidence Regulation Neurons in Language Models
par: Stolfo, Alessandro, et autres
Publié: (2024)

Multilingual Instruction Tuning With Just a Pinch of Multilinguality
par: Shaham, Uri, et autres
Publié: (2024)

Instructed to Bias: Instruction-Tuned Language Models Exhibit Emergent Cognitive Bias
par: Itzhak, Itay, et autres
Publié: (2023)

Mafin: Enhancing Black-Box Embeddings with Model Augmented Fine-Tuning
par: Zhang, Mingtian, et autres
Publié: (2024)

Structured RAG for Answering Aggregative Questions
par: Koshorek, Omri, et autres
Publié: (2025)

Anchored Supervised Fine-Tuning
par: Zhu, He, et autres
Publié: (2025)

Generating Fine Details of Entity Interactions
par: Gu, Xinyi, et autres
Publié: (2025)

Pre-training LLM without Learning Rate Decay Enhances Supervised Fine-Tuning
par: Yano, Kazuki, et autres
Publié: (2026)

Ignore the KL Penalty! Boosting Exploration on Critical Tokens to Enhance RL Fine-Tuning
par: Vassoyan, Jean, et autres
Publié: (2025)

Structure-Guided Entity Resolution: Fine-Tuning LLMs for Robust Name Matching in Complex Linguistic Contexts
par: Chourasia, Shivam, et autres
Publié: (2026)

Erasing Conceptual Knowledge from Language Models
par: Gandikota, Rohit, et autres
Publié: (2024)

Towards Understanding Fine-Tuning Mechanisms of LLMs via Circuit Analysis
par: Wang, Xu, et autres
Publié: (2025)

Prompt Tuning for Natural Language to SQL with Embedding Fine-Tuning and RAG
par: Jang, Jisoo, et autres
Publié: (2025)