10 citations · 16 across the 10 of their papers we have counts for
11 papers
Anchor Divergence for Semantic Geometry in Contrastive Learning
Akash Kannan, Kiho Park, Victor Veitch
This paper concerns how semantic context determines geometry in learned vector representations. Similarity is typically measured using cosine similarity, which provides a single fi…
Optimization Dynamics Imprint Semantic Specificity in Contrastive Embedding Norms
Ziwei Su, Junyu Ren, Victor Veitch
Contrastive embedding models trained with scale-invariant losses are typically paired with distance metrics like cosine similarity, effectively ignoring embedding magnitudes. Howev…
The Information Geometry of Softmax: Probing and Steering
Kiho Park, Todd Nief, Yo Joong Choe +1
This paper concerns the question of how AI systems encode semantic structure into the geometric structure of their representation spaces. The motivating observation is that the nat…
Incorporating Hierarchical Semantics in Sparse Autoencoder Architectures
Mark Muchane, Sean Richardson, Kiho Park +1
Sparse dictionary learning (and, in particular, sparse autoencoders) attempts to learn a set of human-understandable concepts that can explain variation on an abstract space. A bas…
Does Editing Provide Evidence for Localization?
Zihao Wang, Victor Veitch
A basic aspiration for interpretability research in large language models is to "localize" semantically meaningful behaviors to particular components within the LLM. There are vari…
The Geometry of Categorical and Hierarchical Concepts in Large Language Models
Kiho Park, Yo Joong Choe, Yibo Jiang +1
The linear representation hypothesis is the informal idea that semantic concepts are encoded as linear directions in the representation spaces of large language models (LLMs). Prev…
On the Origins of Linear Representations in Large Language Models
Yibo Jiang, Goutham Rajendran, Pradeep Ravikumar +2
Recent works have argued that high-level semantic concepts are encoded "linearly" in the representation space of large language models. In this work, we study the origins of such l…
Transforming and Combining Rewards for Aligning Large Language Models
Zihao Wang, Chirag Nagpal, Jonathan Berant +4
A common approach for aligning language models to human preferences is to first learn a reward model from preference data, and then use this reward model to update the language mod…
The Linear Representation Hypothesis and the Geometry of Large Language Models
Kiho Park, Yo Joong Choe, Victor Veitch
Informally, the 'linear representation hypothesis' is the idea that high-level concepts are represented linearly as directions in some representation space. In this paper, we addre…
Causal Context Connects Counterfactual Fairness to Robust Prediction and Group Fairness
Jacy Reese Anthis, Victor Veitch
Counterfactual fairness requires that a person would have been classified in the same way by an AI or other algorithmic system if they had a different protected class, such as a di…
Uncovering Meanings of Embeddings via Partial Orthogonality
Yibo Jiang, Bryon Aragam, Victor Veitch
Machine learning tools often rely on embedding text as vectors of real numbers. In this paper, we study how the semantic structure of language is encoded in the algebraic structure…