Measuring Progress in Dictionary Learning for Language Model Interpretability with Board Game Models

What latent features are encoded in language model (LM) representations? Recent work on training sparse autoencoders (SAEs) to disentangle interpretable features in LM representations has shown significant promise. However, evaluating the quality of these SAEs is difficult because we lack a ground-truth collection of interpretable features that we expect good SAEs to recover. We thus propose to measure progress in interpretable dictionary learning by working in the setting of LMs trained on chess and Othello transcripts. These settings carry natural collections of interpretable features -- for example, "there is a knight on F3" -- which we leverage into $\textit{supervised}$ metrics for SAE quality. To guide progress in interpretable dictionary learning, we introduce a new SAE training technique, $\textit{p-annealing}$, which improves performance on prior unsupervised metrics as well as our new metrics.

Polynomial Precision Dependence Solutions to Alignment Research Center Matrix Completion Problems

We present solutions to the matrix completion problems proposed by the Alignment Research Center that have a polynomial dependence on the precision $\varepsilon$. The motivation for these problems is to enable efficient computation of heuristic estimators to formally evaluate and reason about different quantities of deep neural networks in the interest of AI alignment. Our solutions involve reframing the matrix completion problems as a semidefinite program (SDP) and using recent advances in spectral bundle methods for fast, efficient, and scalable SDP solving.

Fast, Scalable, Warm-Start Semidefinite Programming with Spectral Bundling and Sketching

While semidefinite programming (SDP) has traditionally been limited to moderate-sized problems, recent algorithms augmented with matrix sketching techniques have enabled solving larger SDPs. However, these methods achieve scalability at the cost of an increase in the number of necessary iterations, resulting in slower convergence as the problem size grows. Furthermore, they require iteration-dependent parameter schedules that prohibit effective utilization of warm-start initializations important in practical applications with incrementally-arriving data or mixed-integer programming. We present SpecBM, a provably correct, fast and scalable algorithm for solving massive SDPs that can leverage a warm-start initialization to further accelerate convergence. Our proposed algorithm is a spectral bundle method for solving general SDPs containing both equality and inequality constraints. Moveover, when augmented with an optional matrix sketching technique, our algorithm achieves the dramatically improved scalability of previous work while sustaining convergence speed. We empirically demonstrate the effectiveness of our method, both with and without warm-starting, across multiple applications with large instances. For example, on a problem with 600 million decision variables, SpecBM achieved a solution of standard accuracy in less than 7 minutes, where the previous state-of-the-art scalable SDP solver requires more than 16 hours. Our method solves an SDP with more than 10^13 decision variables on a single machine with 16 cores and no more than 128GB RAM; the previous state-of-the-art method had not achieved an accurate solution after 72 hours on the same instance. We make our implementation in pure JAX publicly available.

Efficient Nearest Neighbor Search for Cross-Encoder Models using Matrix Factorization

Efficient k-nearest neighbor search is a fundamental task, foundational for many problems in NLP. When the similarity is measured by dot-product between dual-encoder vectors or $\ell_2$-distance, there already exist many scalable and efficient search methods. But not so when similarity is measured by more accurate and expensive black-box neural similarity models, such as cross-encoders, which jointly encode the query and candidate neighbor. The cross-encoders' high computational cost typically limits their use to reranking candidates retrieved by a cheaper model, such as dual encoder or TF-IDF. However, the accuracy of such a two-stage approach is upper-bounded by the recall of the initial candidate set, and potentially requires additional training to align the auxiliary retrieval model with the cross-encoder model. In this paper, we present an approach that avoids the use of a dual-encoder for retrieval, relying solely on the cross-encoder. Retrieval is made efficient with CUR decomposition, a matrix decomposition approach that approximates all pairwise cross-encoder distances from a small subset of rows and columns of the distance matrix. Indexing items using our approach is computationally cheaper than training an auxiliary dual-encoder model through distillation. Empirically, for k > 10, our approach provides test-time recall-vs-computational cost trade-offs superior to the current widely-used methods that re-rank items retrieved using a dual-encoder or TF-IDF.

Entity Linking and Discovery via Arborescence-based Supervised Clustering

Previous work has shown promising results in performing entity linking by measuring not only the affinities between mentions and entities but also those amongst mentions. In this paper, we present novel training and inference procedures that fully utilize mention-to-mention affinities by building minimum arborescences (i.e., directed spanning trees) over mentions and entities across documents in order to make linking decisions. We also show that this method gracefully extends to entity discovery, enabling the clustering of mentions that do not have an associated entity in the knowledge base. We evaluate our approach on the Zero-Shot Entity Linking dataset and MedMentions, the largest publicly available biomedical dataset, and show significant improvements in performance for both entity linking and discovery compared to identically parameterized models. We further show significant efficiency improvements with only a small loss in accuracy over previous work, which use more computationally expensive models.

Relation Matters in Sampling: A Scalable Multi-Relational Graph Neural Network for Drug-Drug Interaction Prediction

Sampling is an established technique to scale graph neural networks to large graphs. Current approaches however assume the graphs to be homogeneous in terms of relations and ignore relation types, critically important in biomedical graphs. Multi-relational graphs contain various types of relations that usually come with variable frequency and have different importance for the problem at hand. We propose an approach to modeling the importance of relation types for neighborhood sampling in graph neural networks and show that we can learn the right balance: relation-type probabilities that reflect both frequency and importance. Our experiments on drug-drug interaction prediction show that state-of-the-art graph neural networks profit from relation-dependent sampling in terms of both accuracy and efficiency.

Low Resource Recognition and Linking of Biomedical Concepts from a Large Ontology

Tools to explore scientific literature are essential for scientists, especially in biomedicine, where about a million new papers are published every year. Many such tools provide users the ability to search for specific entities (e.g. proteins, diseases) by tracking their mentions in papers. PubMed, the most well known database of biomedical papers, relies on human curators to add these annotations. This can take several weeks for new papers, and not all papers get tagged. Machine learning models have been developed to facilitate the semantic indexing of scientific papers. However their performance on the more comprehensive ontologies of biomedical concepts does not reach the levels of typical entity recognition problems studied in NLP. In large part this is due to their low resources, where the ontologies are large, there is a lack of descriptive text defining most entities, and labeled data can only cover a small portion of the ontology. In this paper, we develop a new model that overcomes these challenges by (1) generalizing to entities unseen at training time, and (2) incorporating linking predictions into the mention segmentation decisions. Our approach achieves new state-of-the-art results for the UMLS ontology in both traditional recognition/linking (+8 F1 pts) as well as semantic indexing-based evaluation (+10 F1 pts).

Fairkit, Fairkit, on the Wall, Who's the Fairest of Them All? Supporting Data Scientists in Training Fair Models

Modern software relies heavily on data and machine learning, and affects decisions that shape our world. Unfortunately, recent studies have shown that because of biases in data, software systems frequently inject bias into their decisions, from producing better closed caption transcriptions of men's voices than of women's voices to overcharging people of color for financial loans. To address bias in machine learning, data scientists need tools that help them understand the trade-offs between model quality and fairness in their specific data domains. Toward that end, we present fairkit-learn, a toolkit for helping data scientists reason about and understand fairness. Fairkit-learn works with state-of-the-art machine learning tools and uses the same interfaces to ease adoption. It can evaluate thousands of models produced by multiple machine learning algorithms, hyperparameters, and data permutations, and compute and visualize a small Pareto-optimal set of models that describe the optimal trade-offs between fairness and quality. We evaluate fairkit-learn via a user study with 54 students, showing that students using fairkit-learn produce models that provide a better balance between fairness and quality than students using scikit-learn and IBM AI Fairness 360 toolkits. With fairkit-learn, users can select models that are up to 67% more fair and 10% more accurate than the models they are likely to train with scikit-learn.

Clustering-based Inference for Zero-Shot Biomedical Entity Linking

Due to large number of entities in biomedical knowledge bases, only a small fraction of entities have corresponding labelled training data. This necessitates a zero-shot entity linking model which is able to link mentions of unseen entities using learned representations of entities. Existing zero-shot entity linking models however link each mention independently, ignoring the inter/intra-document relationships between the entity mentions. These relations can be very useful for linking mentions in biomedical text where linking decisions are often difficult due mentions having a generic or a highly specialized form. In this paper, we introduce a model in which linking decisions can be made not merely by linking to a KB entity but also by grouping multiple mentions together via clustering and jointly making linking predictions. In experiments on the largest publicly available biomedical dataset, we improve the best independent prediction for zero-shot entity linking by 2.5 points of accuracy, and our joint inference model further improves entity linking by 1.8 points.