Causality $\neq$ Invariance: Function and Concept Vectors in LLMs
Fuente:
arXiv
Saved in:
| Main Authors: | Opiełka, Gustaw, Rosenbusch, Hannes, Stevenson, Claire E. |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
Analogical Reasoning Inside Large Language Models: Concept Vectors and the Limits of Abstraction
by: Opiełka, Gustaw, et al.
Published: (2025)
by: Opiełka, Gustaw, et al.
Published: (2025)
Do Large Language Models Solve ARC Visual Analogies Like People Do?
by: Opiełka, Gustaw, et al.
Published: (2024)
by: Opiełka, Gustaw, et al.
Published: (2024)
Beyond Single Concept Vector: Modeling Concept Subspace in LLMs with Gaussian Distribution
by: Zhao, Haiyan, et al.
Published: (2024)
by: Zhao, Haiyan, et al.
Published: (2024)
What makes for an enjoyable protagonist? An analysis of character warmth and competence
by: Rosenbusch, Hannes
Published: (2026)
by: Rosenbusch, Hannes
Published: (2026)
Transformer See, Transformer Do: Copying as an Intermediate Step in Learning Analogical Reasoning
by: Hellwig, Philipp, et al.
Published: (2026)
by: Hellwig, Philipp, et al.
Published: (2026)
Vector Quantized Latent Concepts: A Scalable Alternative to Clustering-Based Concept Discovery
by: Yu, Xuemin, et al.
Published: (2026)
by: Yu, Xuemin, et al.
Published: (2026)
LLM_annotate: A Python package for annotating and analyzing fiction characters
by: Rosenbusch, Hannes
Published: (2025)
by: Rosenbusch, Hannes
Published: (2025)
Saliency Suppressed, Semantics Surfaced: Visual Transformations in Neural Networks and the Brain
by: Opiełka, Gustaw, et al.
Published: (2024)
by: Opiełka, Gustaw, et al.
Published: (2024)
Function Vectors in Large Language Models
by: Todd, Eric, et al.
Published: (2023)
by: Todd, Eric, et al.
Published: (2023)
On Lexical Invariance on Multisets and Graphs
by: Zhang, Muhan
Published: (2024)
by: Zhang, Muhan
Published: (2024)
Failure Modes of LLMs for Causal Reasoning on Narratives
by: Yamin, Khurram, et al.
Published: (2024)
by: Yamin, Khurram, et al.
Published: (2024)
CRVQ: Channel-Relaxed Vector Quantization for Extreme Compression of LLMs
by: Xu, Yuzhuang, et al.
Published: (2024)
by: Xu, Yuzhuang, et al.
Published: (2024)
Mathematical Reasoning via Intervention-Based Time-Series Causal Discovery Using LLMs as Concept Mastery Simulators
by: Okita, Tsuyoshi
Published: (2026)
by: Okita, Tsuyoshi
Published: (2026)
Trained on Tokens, Calibrated on Concepts: The Emergence of Semantic Calibration in LLMs
by: Nakkiran, Preetum, et al.
Published: (2025)
by: Nakkiran, Preetum, et al.
Published: (2025)
Can LLMs Learn New Concepts Incrementally without Forgetting?
by: Zheng, Junhao, et al.
Published: (2024)
by: Zheng, Junhao, et al.
Published: (2024)
Relational Knowledge Distillation Using Fine-tuned Function Vectors
by: Kang, Andrea, et al.
Published: (2026)
by: Kang, Andrea, et al.
Published: (2026)
Refusal in LLMs is an Affine Function
by: Marshall, Thomas, et al.
Published: (2024)
by: Marshall, Thomas, et al.
Published: (2024)
Cyclic Ablation: Testing Concept Localization against Functional Regeneration in AI
by: Kapelko, Eduard
Published: (2025)
by: Kapelko, Eduard
Published: (2025)
Causally Testing Gender Bias in LLMs: A Case Study on Occupational Bias
by: Chen, Yuen, et al.
Published: (2022)
by: Chen, Yuen, et al.
Published: (2022)
NEAT: Concept driven Neuron Attribution in LLMs
by: Kavuri, Vivek Hruday, et al.
Published: (2025)
by: Kavuri, Vivek Hruday, et al.
Published: (2025)
Self-Supervised Learning for Neural Topic Models with Variance-Invariance-Covariance Regularization
by: Xu, Weiran, et al.
Published: (2025)
by: Xu, Weiran, et al.
Published: (2025)
Shifting Perspectives: Steering Vectors for Robust Bias Mitigation in LLMs
by: Siddique, Zara, et al.
Published: (2025)
by: Siddique, Zara, et al.
Published: (2025)
Can Post-Training Transform LLMs into Causal Reasoners?
by: Chen, Junqi, et al.
Published: (2026)
by: Chen, Junqi, et al.
Published: (2026)
CauScientist: Teaching LLMs to Respect Data for Causal Discovery
by: Peng, Bo, et al.
Published: (2026)
by: Peng, Bo, et al.
Published: (2026)
Are the Values of LLMs Structurally Aligned with Humans? A Causal Perspective
by: Kang, Yipeng, et al.
Published: (2024)
by: Kang, Yipeng, et al.
Published: (2024)
Are some books better than others?
by: Rosenbusch, Hannes, et al.
Published: (2025)
by: Rosenbusch, Hannes, et al.
Published: (2025)
MedConceptsQA: Open Source Medical Concepts QA Benchmark
by: Shoham, Ofir Ben, et al.
Published: (2024)
by: Shoham, Ofir Ben, et al.
Published: (2024)
Kernelized Concept Erasure
by: Ravfogel, Shauli, et al.
Published: (2022)
by: Ravfogel, Shauli, et al.
Published: (2022)
Steer2Adapt: Dynamically Composing Steering Vectors Elicits Efficient Adaptation of LLMs
by: Han, Pengrui, et al.
Published: (2026)
by: Han, Pengrui, et al.
Published: (2026)
Which books do I like?
by: Rosenbusch, Hannes, et al.
Published: (2025)
by: Rosenbusch, Hannes, et al.
Published: (2025)
CausalEvolve: Towards Open-Ended Discovery with Causal Scratchpad
by: Chen, Yongqiang, et al.
Published: (2026)
by: Chen, Yongqiang, et al.
Published: (2026)
Causality $\neq$ Decodability, and Vice Versa: Lessons from Interpreting Counting ViTs
by: Huang, Lianghuan, et al.
Published: (2025)
by: Huang, Lianghuan, et al.
Published: (2025)
Towards Compositionality in Concept Learning
by: Stein, Adam, et al.
Published: (2024)
by: Stein, Adam, et al.
Published: (2024)
Linear Adversarial Concept Erasure
by: Ravfogel, Shauli, et al.
Published: (2022)
by: Ravfogel, Shauli, et al.
Published: (2022)
LLM Pretraining with Continuous Concepts
by: Tack, Jihoon, et al.
Published: (2025)
by: Tack, Jihoon, et al.
Published: (2025)
Predicting Where Steering Vectors Succeed
by: Billa, Jayadev
Published: (2026)
by: Billa, Jayadev
Published: (2026)
Concurrency without Model Changes: Future-based Asynchronous Function Calling for LLMs
by: Feng, Guangyu, et al.
Published: (2026)
by: Feng, Guangyu, et al.
Published: (2026)
One Example Shown, Many Concepts Known! Counterexample-Driven Conceptual Reasoning in Mathematical LLMs
by: Li, Yinghui, et al.
Published: (2025)
by: Li, Yinghui, et al.
Published: (2025)
Concept Bottleneck Large Language Models
by: Sun, Chung-En, et al.
Published: (2024)
by: Sun, Chung-En, et al.
Published: (2024)
Adaptive Task Vectors for Large Language Models
by: Kang, Joonseong, et al.
Published: (2025)
by: Kang, Joonseong, et al.
Published: (2025)
Similar Items
-
Analogical Reasoning Inside Large Language Models: Concept Vectors and the Limits of Abstraction
by: Opiełka, Gustaw, et al.
Published: (2025) -
Do Large Language Models Solve ARC Visual Analogies Like People Do?
by: Opiełka, Gustaw, et al.
Published: (2024) -
Beyond Single Concept Vector: Modeling Concept Subspace in LLMs with Gaussian Distribution
by: Zhao, Haiyan, et al.
Published: (2024) -
What makes for an enjoyable protagonist? An analysis of character warmth and competence
by: Rosenbusch, Hannes
Published: (2026) -
Transformer See, Transformer Do: Copying as an Intermediate Step in Learning Analogical Reasoning
by: Hellwig, Philipp, et al.
Published: (2026)