Search Results for author:
Found 17 papers, 9 papers with code
Belief in the Machine: Investigating Epistemological Blind Spots of Language Models
These findings highlight significant concerns about current LMs' ability to reason about truth, belief, and knowledge while emphasizing the need for advancements in these areas before broad deployment in critical sectors.
A Reply to Makelov et al. (2023)'s "Interpretability Illusion" Arguments
We respond to the recent paper by Makelov et al. (2023), which reviews subspace interchange intervention methods like distributed alignment search (DAS; Geiger et al. 2023) and claims that these methods potentially cause "interpretability illusions".
Interpretability at Scale: Identifying Causal Mechanisms in Alpaca
With Boundless DAS, we discover that Alpaca does this by implementing a causal model with two interpretable boolean variables.
Finding Alignments Between Interpretable Causal Variables and Distributed Neural Representations
In DAS, we find the alignment between high-level and low-level models using gradient descent rather than conducting a brute-force search, and we allow individual neurons to play multiple distinct roles by analyzing representations in non-standard bases-distributed representations.
Causal Abstraction: A Theoretical Foundation for Mechanistic Interpretability
Causal abstraction provides a theoretical foundation for mechanistic interpretability, the field concerned with providing intelligible algorithms that are faithful simplifications of the known, but opaque low-level details of black box AI models.
Causal Abstraction with Soft Interventions
Causal abstraction provides a theory describing how several causal models can represent the same system at different levels of detail.
Holistic Evaluation of Language Models
We present Holistic Evaluation of Language Models (HELM) to improve the transparency of language models.
Causal Distillation for Language Models
Distillation efforts have led to language models that are more compact and efficient without serious drops in performance.
Inducing Causal Structure for Interpretable Neural Networks
In IIT, we (1) align variables in a causal model (e. g., a deterministic program or Bayesian network) with representations in a neural model and (2) train the neural model to match the counterfactual behavior of the causal model on a base input when aligned representations in both models are set to be the value they would be for a source input.
On the Opportunities and Risks of Foundation Models
AI is undergoing a paradigm shift with the rise of models (e. g., BERT, DALL-E, GPT-3) that are trained on broad data at scale and are adaptable to a wide range of downstream tasks.
A Topological Perspective on Causal Inference
This paper presents a topological learning-theoretic perspective on causal inference by introducing a series of topologies defined on general spaces of structural causal models (SCMs).
Causal Abstractions of Neural Networks
Structural analysis methods (e. g., probing and feature attribution) are increasingly important tools for neural network analysis.
Intention as Commitment toward Time
The first contribution is a logic for reasoning about intention, time and belief, in which assumptions of intentions are represented by preconditions of intended actions.
Probabilistic Reasoning across the Causal Hierarchy
We propose a formalization of the three-tier causal hierarchy of association, intervention, and counterfactuals as a series of probabilistic logical languages.
On Open-Universe Causal Reasoning
We extend two kinds of causal models, structural equation models and simulation models, to infinite variable spaces.
On the Conditional Logic of Simulation Models
We propose analyzing conditional reasoning by appeal to a notion of intervention on a simulation program, formalizing and subsuming a number of approaches to conditional thinking in the recent AI literature.
