23 accepted papers
Do the chains of thought (CoT) of reasoning Large Language Models (LLMs) reflect their internal computation? In this paper, we provide evidence of \textit{performative} CoT, where a model becomes strongly confident in its final answer, but continues generating excess tokens without revealing its int…
Activation decomposition methods in language models are tightly coupled to geometric assumptions on how concepts are realized in activation space. Existing approaches search for individual global directions, implicitly assuming linear separability, which overlooks concepts with nonlinear or multi-di…
How do language models (LMs) represent characters’ beliefs, especially when those beliefs may differ from reality? This question lies at the heart of understanding the Theory of Mind (ToM) capabilities of LMs. We analyze LMs' ability to reason about characters’ beliefs using causal mediation and abs…
A key component of in-context reasoning is the ability of language models (LMs) to bind entities for later retrieval. For example, an LM might represent *Ann loves pie* by binding *Ann* to *pie*, allowing it to later retrieve *Ann* when asked *Who loves pie?* Prior research on short lists of bound…
Fine-grained steering of language model outputs is essential for safety and reliability. Prompting and finetuning are widely used to achieve these goals, but interpretability researchers have proposed a variety of representation-based techniques as well, including sparse autoencoders (SAEs), linear…
Automated interpretability pipelines generate natural language descriptions for the concepts represented by features in large language models (LLMs), such as “plants” or “the first word in a sentence”. These descriptions are derived using inputs that activate the feature, which may be a dimension or…
Variable binding---the ability to associate variables with values---is fundamental to symbolic computation and cognition. Although classical architectures typically implement variable binding via addressable memory, it is not well understood how modern neural networks lacking built-in binding operat…
Mechanistic interpretability has made great strides in identifying neural network features (e.g., directions in hidden activation space) that mediate concepts (e.g., *the birth year of a Nobel laureate*) and enable predictable manipulation. Distributed alignment search (DAS) leverages supervision fr…
How can we know whether new mechanistic interpretability methods achieve real improvements? In pursuit of lasting evaluation standards, we propose MIB, a Mechanistic Interpretability Benchmark, with two tracks spanning four tasks and five models. MIB favors methods that precisely and concisely recov…
Mechanistic interpretability aims to attribute high-level model behaviors to specific, interpretable learned features. It is hypothesized that these features manifest as directions or low-dimensional subspaces within activation space. Accordingly, recent studies have explored the identification and…
Individual neurons participate in the representation of multiple high-level concepts. To what extent can different interpretability methods successfully disentangle these roles? To help address this question, we introduce RAVEL (Resolving Attribute-Value Entanglements in Language Models), a dataset…
Parameter-efficient finetuning (PEFT) methods seek to adapt large neural models via updates to a small number of *weights*. However, much prior interpretability work has shown that *representations* encode rich semantic information, suggesting that editing representations might be a more powerful al…
Although CLIPScore is a powerful generic metric that captures the similarity between a text and an image, it fails to distinguish between a caption that is meant to complement the information in an image and a description that is meant to replace an image entirely, e.g., for accessibility. We addres…
Interventions on model-internal states are fundamental operations in many areas of AI, including model editing, steering, robustness, and interpretability. To facilitate such research, we introduce pyvene, an open-source Python library that supports customizable interventions on a range of different…
Explainability methods for NLP systems encounter a version of the fundamental problem of causal inference: for a given ground-truth input text, we never truly observe the counterfactual texts necessary for isolating the causal effects of model representations on outputs. In response, many explainabi…
Obtaining human-interpretable explanations of large, general-purpose language models is an urgent goal for AI safety. However, it is just as important that our interpretability methods are faithful to the causal dynamics underlying model behavior and able to robustly generalize to unseen inputs. Dis…
A number of recent benchmarks seek to assess how well models handle natural language negation. However, these benchmarks lack the controlled example paradigms that would allow us to infer whether a model had truly learned how negation morphemes semantically scope. To fill these analytical gaps, we p…
The increasing size and complexity of modern ML systems has improved their predictive capabilities but made their behavior harder to explain. Many techniques for model explanation have been developed in response, but we lack clear criteria for assessing these techniques. In this paper, we cast model…
Distillation efforts have led to language models that are more compact and efficient without serious drops in performance. The standard approach to distillation trains a student model against two objectives: a task-specific objective (e.g., language modeling) and an imitation objective that encourag…
In many areas, we have well-founded insights about causal structure that would be useful to bring into our trained models while still allowing them to learn in a data-driven fashion. To achieve this, we present the new method of interchange intervention training (IIT). In IIT, we (1) align variables…
Structural analysis methods (e.g., probing and feature attribution) are increasingly important tools for neural network analysis. We propose a new structural analysis method grounded in a formal theory of causal abstraction that provides rich characterizations of model-internal representations and t…
We introduce DynaSent (‘Dynamic Sentiment’), a new English-language benchmark task for ternary (positive/negative/neutral) sentiment analysis. DynaSent combines naturally occurring sentences with sentences created using the open-source Dynabench Platform, which facilities human-and-model-in-the-loop…
We introduce Dynabench, an open-source platform for dynamic dataset creation and model benchmarking. Dynabench runs in a web browser and supports human-and-model-in-the-loop dataset creation: annotators seek to create examples that a target model will misclassify, but that another person will not. I…