Adam Stein

Qing Lyu, Shreya Havaldar, Adam Stein et al.

While Chain-of-Thought (CoT) prompting boosts Language Models' (LM) performance on a gamut of complex reasoning tasks, the generated reasoning chain does not necessarily reflect how the model arrives at the answer (aka. faithfulness). We propose Faithful CoT, a reasoning framework involving two stages: Translation (Natural Language query $\rightarrow$ symbolic reasoning chain) and Problem Solving (reasoning chain $\rightarrow$ answer), using an LM and a deterministic solver respectively. This guarantees that the reasoning chain provides a faithful explanation of the final answer. Aside from interpretability, Faithful CoT also improves empirical performance: it outperforms standard CoT on 9 of 10 benchmarks from 4 diverse domains, with a relative accuracy gain of 6.3% on Math Word Problems (MWP), 3.4% on Planning, 5.5% on Multi-hop Question Answering (QA), and 21.4% on Relational Inference. Furthermore, with GPT-4 and Codex, it sets the new state-of-the-art few-shot performance on 7 datasets (with 95.0+ accuracy on 6 of them), showing a strong synergy between faithfulness and accuracy.

Yinjun Wu, Adam Stein, Jacob Gardner et al.

Sample re-weighting strategies provide a promising mechanism to deal with imperfect training data in machine learning, such as noisily labeled or class-imbalanced data. One such strategy involves formulating a bi-level optimization problem called the meta re-weighting problem, whose goal is to optimize performance on a small set of perfect pivotal samples, called meta samples. Many approaches have been proposed to efficiently solve this problem. However, all of them assume that a perfect meta sample set is already provided while we observe that the selections of meta sample set is performance critical. In this paper, we study how to learn to identify such a meta sample set from a large, imperfect training set, that is subsequently cleaned and used to optimize performance in the meta re-weighting setting. We propose a learning framework which reduces the meta samples selection problem to a weighted K-means clustering problem through rigorously theoretical analysis. We propose two clustering methods within our learning framework, Representation-based clustering method (RBC) and Gradient-based clustering method (GBC), for balancing performance and computational efficiency. Empirical studies demonstrate the performance advantage of our methods over various baseline methods.

Shreya Havaldar, Adam Stein, Eric Wong et al.

Meaningfully comparing language models is challenging with current explanation methods. Current explanations are overwhelming for humans due to large vocabularies or incomparable across models. We present TopEx, an explanation method that enables a level playing field for comparing language models via model-agnostic topics. We demonstrate how TopEx can identify similarities and differences between DistilRoBERTa and GPT-2 on a variety of NLP tasks.

Aaditya Naik, Adam Stein, Yinjun Wu et al.

Finding errors in machine learning applications requires a thorough exploration of their behavior over data. Existing approaches used by practitioners are often ad-hoc and lack the abstractions needed to scale this process. We present TorchQL, a programming framework to evaluate and improve the correctness of machine learning applications. TorchQL allows users to write queries to specify and check integrity constraints over machine learning models and datasets. It seamlessly integrates relational algebra with functional programming to allow for highly expressive queries using only eight intuitive operators. We evaluate TorchQL on diverse use-cases including finding critical temporal inconsistencies in objects detected across video frames in autonomous driving, finding data imputation errors in time-series medical records, finding data labeling errors in real-world images, and evaluating biases and constraining outputs of language models. Our experiments show that TorchQL enables up to 13x faster query executions than baselines like Pandas and MongoDB, and up to 40% shorter queries than native Python. We also conduct a user study and find that TorchQL is natural enough for developers familiar with Python to specify complex integrity constraints.

Adam Stein, Aaditya Naik, Yinjun Wu et al.

Concept-based interpretability methods offer a lens into the internals of foundation models by decomposing their embeddings into high-level concepts. These concept representations are most useful when they are compositional, meaning that the individual concepts compose to explain the full sample. We show that existing unsupervised concept extraction methods find concepts which are not compositional. To automatically discover compositional concept representations, we identify two salient properties of such representations, and propose Compositional Concept Extraction (CCE) for finding concepts which obey these properties. We evaluate CCE on five different datasets over image and text data. Our evaluation shows that CCE finds more compositional concept representations than baselines and yields better accuracy on four downstream classification tasks. Code and data are available at https://github.com/adaminsky/compositional_concepts .

Cassandra Goldberg, Chaehyeon Kim, Adam Stein et al.

Concept vectors aim to enhance model interpretability by linking internal representations with human-understandable semantics, but their utility is often limited by noisy and inconsistent activations. In this work, we uncover a clear pattern within the noise, which we term the SuperActivator Mechanism: while in-concept and out-of-concept activations overlap considerably, the token activations in the extreme high tail of the in-concept distribution provide a reliable signal of concept presence. We demonstrate the generality of this mechanism by showing that SuperActivator tokens consistently outperform standard vector-based and prompting concept detection approaches, achieving up to a 14% higher F1 score across image and text modalities, model architectures, model layers, and concept extraction techniques. Finally, we leverage SuperActivator tokens to improve feature attributions for concepts.

Shreya Havaldar, Adam Stein, Eric Wong et al.

Successful communication depends on the speaker's intended style (i.e., what the speaker is trying to convey) aligning with the listener's interpreted style (i.e., what the listener perceives). However, cultural differences often lead to misalignment between the two; for example, politeness is often lost in translation. We characterize the ways that LLMs fail to translate style - biasing translations towards neutrality and performing worse in non-Western languages. We mitigate these failures with RASTA (Retrieval-Augmented STylistic Alignment), a method that leverages learned stylistic concepts to encourage LLM translation to appropriately convey cultural communication norms and align style.

Adam Stein, Yinjun Wu, Eric Wong et al.

It is well-known that real-world changes constituting distribution shift adversely affect model performance. How to characterize those changes in an interpretable manner is poorly understood. Existing techniques to address this problem take the form of shift explanations that elucidate how to map samples from the original distribution toward the shifted one by reducing the disparity between these two distributions. However, these methods can introduce group irregularities, leading to explanations that are less feasible and robust. To address these issues, we propose Group-aware Shift Explanations (GSE), a method that produces interpretable explanations by leveraging worst-group optimization to rectify group irregularities. We demonstrate how GSE not only maintains group structures, such as demographic and hierarchical subpopulations, but also enhances feasibility and robustness in the resulting explanations in a wide range of tabular, language, and image settings.