Cover Image

Language Models use Lookbacks to Track Beliefs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Prakash, Nikhil, Shapira, Natalie, Sharma, Arnab Sen, Riedl, Christoph, Belinkov, Yonatan, Shaham, Tamar Rott, Bau, David, Geiger, Atticus
Format:	Preprint
Published:	2025
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity Tracking
by: Prakash, Nikhil, et al.
Published: (2024)

Linearity of Relation Decoding in Transformer Language Models
by: Hernandez, Evan, et al.
Published: (2023)

The Dual Mechanisms of Spatial Reasoning in Vision-Language Models
by: Cui, Kelly, et al.
Published: (2026)

Pitfalls in Evaluating Interpretability Agents
by: Haklay, Tal, et al.
Published: (2026)

Locating and Editing Factual Associations in Mamba
by: Sharma, Arnab Sen, et al.
Published: (2024)

LLMs Process Lists With General Filter Heads
by: Sharma, Arnab Sen, et al.
Published: (2025)

Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models
by: Marks, Samuel, et al.
Published: (2024)

Back Attention: Understanding and Enhancing Multi-Hop Reasoning in Large Language Models
by: Yu, Zeping, et al.
Published: (2025)

Mixing Mechanisms: How Language Models Retrieve Bound Entities In-Context
by: Gur-Arieh, Yoav, et al.
Published: (2025)

Position-aware Automatic Circuit Discovery
by: Haklay, Tal, et al.
Published: (2025)

ContraSim -- Analyzing Neural Representations Based on Contrastive Learning
by: Rahamim, Adir, et al.
Published: (2023)

REVS: Unlearning Sensitive Information in Language Models via Rank Editing in the Vocabulary Space
by: Ashuach, Tomer, et al.
Published: (2024)

A Vision Check-up for Language Models
by: Sharma, Pratyusha, et al.
Published: (2024)

Function Vectors in Large Language Models
by: Todd, Eric, et al.
Published: (2023)

Constructing Interpretable Features from Compositional Neuron Groups
by: Shafran, Or, et al.
Published: (2025)

The Shape of Beliefs: Geometry, Dynamics, and Interventions along Representation Manifolds of Language Models' Posteriors
by: Sarfati, Raphaël, et al.
Published: (2026)

Backward Lens: Projecting Language Model Gradients into the Vocabulary Space
by: Katz, Shahar, et al.
Published: (2024)

Elucidating Mechanisms of Demographic Bias in LLMs for Healthcare
by: Ahsan, Hiba, et al.
Published: (2025)

Reasoning Theater: Disentangling Model Beliefs from Chain-of-Thought
by: Boppana, Siddharth, et al.
Published: (2026)

RAVEL: Evaluating Interpretability Methods on Disentangling Language Model Representations
by: Huang, Jing, et al.
Published: (2024)

Arithmetic Without Algorithms: Language Models Solve Math With a Bag of Heuristics
by: Nikankin, Yaniv, et al.
Published: (2024)

Have Faith in Faithfulness: Going Beyond Circuit Overlap When Finding Model Mechanisms
by: Hanna, Michael, et al.
Published: (2024)

From Directions to Regions: Decomposing Activations in Language Models via Local Geometry
by: Shafran, Or, et al.
Published: (2026)

ScoNe: Benchmarking Negation Reasoning in Language Models With Fine-Tuning and In-Context Learning
by: She, Jingyuan Selena, et al.
Published: (2023)

How Causal Abstraction Underpins Computational Explanation
by: Geiger, Atticus, et al.
Published: (2025)

How Do Transformers Learn Variable Binding in Symbolic Programs?
by: Wu, Yiwei, et al.
Published: (2025)

Concept-Best-Matching: Evaluating Compositionality in Emergent Communication
by: Carmeli, Boaz, et al.
Published: (2024)

ReFACT: Updating Text-to-Image Models by Editing the Text Encoder
by: Arad, Dana, et al.
Published: (2023)

Are formal and functional linguistic mechanisms dissociated in language models?
by: Hanna, Michael, et al.
Published: (2025)

SAEs Are Good for Steering -- If You Select the Right Features
by: Arad, Dana, et al.
Published: (2025)

Leveraging Prototypical Representations for Mitigating Social Bias without Demographic Information
by: Iskander, Shadi, et al.
Published: (2024)

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

Vision-Language Binding in In-Context Image Generation
by: Ge, Chris, et al.
Published: (2026)

DEPTH: Discourse Education through Pre-Training Hierarchically
by: Bamberger, Zachary, et al.
Published: (2024)

A Multimodal Automated Interpretability Agent
by: Shaham, Tamar Rott, et al.
Published: (2024)

Stories in Space: In-Context Learning Trajectories in Conceptual Belief Space
by: Bigelow, Eric, et al.
Published: (2026)

Follow the Flow: On Information Flow Across Textual Tokens in Text-to-Image Models
by: Kaplan, Guy, et al.
Published: (2025)

Unified Concept Editing in Diffusion Models
by: Gandikota, Rohit, et al.
Published: (2023)

Fast Forwarding Low-Rank Training
by: Rahamim, Adir, et al.
Published: (2024)

Differentiable Faithfulness Alignment for Cross-Model Circuit Transfer
by: Shao, Shun, et al.
Published: (2026)