Cover Image

Interpretability Illusions in the Generalization of Simplified Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Friedman, Dan, Lampinen, Andrew, Dixon, Lucas, Chen, Danqi, Ghandeharioun, Asma
Format:	Preprint
Published:	2023
Subjects:	Machine Learning Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

The Heuristic Core: Understanding Subnetwork Generalization in Pretrained Language Models
by: Bhaskar, Adithya, et al.
Published: (2024)

Patchscopes: A Unifying Framework for Inspecting Hidden Representations of Language Models
by: Ghandeharioun, Asma, et al.
Published: (2024)

Representing Rule-based Chatbots with Transformers
by: Friedman, Dan, et al.
Published: (2024)

Extracting Rule-based Descriptions of Attention Features in Transformers
by: Friedman, Dan, et al.
Published: (2025)

Think Before You Lie: How Reasoning Leads to Honesty
by: Yuan, Ann, et al.
Published: (2026)

When Can Transformers Count to n?
by: Yehudai, Gilad, et al.
Published: (2024)

How to Train Long-Context Language Models (Effectively)
by: Gao, Tianyu, et al.
Published: (2024)

QuRating: Selecting High-Quality Data for Training Language Models
by: Wettig, Alexander, et al.
Published: (2024)

Lory: Fully Differentiable Mixture-of-Experts for Autoregressive Language Model Pre-training
by: Zhong, Zexuan, et al.
Published: (2024)

Towards Unifying Interpretability and Control: Evaluation via Intervention
by: Bhalla, Usha, et al.
Published: (2024)

SimPO: Simple Preference Optimization with a Reference-Free Reward
by: Meng, Yu, et al.
Published: (2024)

Linear representations in language models can change dramatically over a conversation
by: Lampinen, Andrew Kyle, et al.
Published: (2026)

The broader spectrum of in-context learning
by: Lampinen, Andrew Kyle, et al.
Published: (2024)

How do language models learn facts? Dynamics, curricula and hallucinations
by: Zucchet, Nicolas, et al.
Published: (2025)

The Illusion of Stochasticity in LLMs
by: Gu, Xiangming, et al.
Published: (2026)

Retaining by Doing: The Role of On-Policy Data in Mitigating Forgetting
by: Chen, Howard, et al.
Published: (2025)

A Reply to Makelov et al. (2023)'s "Interpretability Illusion" Arguments
by: Wu, Zhengxuan, et al.
Published: (2024)

Latent learning: episodic memory complements parametric learning by enabling flexible reuse of experiences
by: Lampinen, Andrew Kyle, et al.
Published: (2025)

The in-context inductive biases of vision-language models differ across modalities
by: Allen, Kelsey, et al.
Published: (2025)

The Illusion of State in State-Space Models
by: Merrill, William, et al.
Published: (2024)

Who's asking? User personas and the mechanics of latent misalignment
by: Ghandeharioun, Asma, et al.
Published: (2024)

Distinct Computations Emerge From Compositional Curricula in In-Context Learning
by: Lee, Jin Hwa, et al.
Published: (2025)

Evaluating Large Language Models at Evaluating Instruction Following
by: Zeng, Zhiyuan, et al.
Published: (2023)

Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning
by: Xia, Mengzhou, et al.
Published: (2023)

The Illusion of Superposition? A Principled Analysis of Latent Thinking in Language Models
by: Rizvi-Martel, Michael, et al.
Published: (2026)

Racing Thoughts: Explaining Contextualization Errors in Large Language Models
by: Lepori, Michael A., et al.
Published: (2024)

Fine-Tuning Language Models with Just Forward Passes
by: Malladi, Sadhika, et al.
Published: (2023)

The Leaderboard Illusion
by: Singh, Shivalika, et al.
Published: (2025)

The Illusion of Certainty: Uncertainty Quantification for LLMs Fails under Ambiguity
by: Tomov, Tim, et al.
Published: (2025)

LoRA vs Full Fine-tuning: An Illusion of Equivalence
by: Shuttleworth, Reece, et al.
Published: (2024)

The Surprising Effectiveness of Negative Reinforcement in LLM Reasoning
by: Zhu, Xinyu, et al.
Published: (2025)

The Illusion of Readiness in Health AI
by: Gu, Yu, et al.
Published: (2025)

Continual Memorization of Factoids in Language Models
by: Chen, Howard, et al.
Published: (2024)

Are UFOs Driving Innovation? The Illusion of Causality in Large Language Models
by: Carro, María Victoria, et al.
Published: (2024)

Putting It All into Context: Simplifying Agents with LCLMs
by: Jiang, Mingjian, et al.
Published: (2025)

Finding Transformer Circuits with Edge Pruning
by: Bhaskar, Adithya, et al.
Published: (2024)

Improving Language Understanding from Screenshots
by: Gao, Tianyu, et al.
Published: (2024)

The Data-Quality Illusion: Rethinking Classifier-Based Quality Filtering for LLM Pretraining
by: Saada, Thiziri Nait, et al.
Published: (2025)

Simplifying Outcomes of Language Model Component Analyses with ELIA
by: Eidt, Aaron Louis, et al.
Published: (2026)

The Illusion of Intervention: Your LLM-Simulated Experiment is an Observational Study
by: Lin, Victoria, et al.
Published: (2026)