With large language models surpassing human performance on an increasing number of benchmarks, we must take a principled approach for targeted evaluation of model capabilities. Inspired by pseudorandomness, we propose pseudointelligence, which captures the maxim that “(perceived) intelligence lies in the eye of the beholder.” That is, that claims of intelligence are meaningful only when their evaluator is taken into account. Concretely, we propose a complexity-theoretic framework of model evaluation cast as a dynamic interaction between a model and a learned evaluator. We demonstrate that this framework can be used to reason about two case studies in language model evaluation, as well as analyze existing evaluation methods.

For humans, language production and comprehension is sensitive to the hierarchical structure of sentences. In natural language processing, past work has questioned how effectively neural sequence models like transformers capture this hierarchical structure when generalizing to structurally novel inputs. We show that transformer language models can learn to generalize hierarchically after training for extremely long periods—far beyond the point when in-domain accuracy has saturated. We call this phenomenon structural grokking. On multiple datasets, structural grokking exhibits inverted U-shaped scaling in model depth: intermediate-depth models generalize better than both very deep and very shallow transformers. When analyzing the relationship between model-internal properties and grokking, we find that optimal depth for grokking can be identified using the tree-structuredness metric of CITATION. Overall, our work provides strong evidence that, with extended training, vanilla transformers discover and use hierarchical structure.

Recursion is a prominent feature of human language, and fundamentally challenging for self-attention due to the lack of an explicit recursive-state tracking mechanism. Consequently, Transformer language models poorly capture long-tail recursive structure and exhibit sample-inefficient syntactic generalization. This work introduces Pushdown Layers, a new self-attention layer that models recursive state via a stack tape that tracks estimated depths of every token in an incremental parse of the observed prefix. Transformer LMs with Pushdown Layers are syntactic language models that autoregressively and synchronously update this stack tape as they predict new tokens, in turn using the stack tape to softly modulate attention over tokens—for instance, learning to “skip” over closed constituents. When trained on a corpus of strings annotated with silver constituency parses, Transformers equipped with Pushdown Layers achieve dramatically better and 3-5x more sample-efficient syntactic generalization, while maintaining similar perplexities. Pushdown Layers are a drop-in replacement for standard self-attention. We illustrate this by finetuning GPT2-medium with Pushdown Layers on an automatically parsed WikiText-103, leading to improvements on several GLUE text classification tasks.

While advances in pre-training have led to dramatic improvements in few-shot learning of NLP tasks, there is limited understanding of what drives successful few-shot adaptation in datasets. In particular, given a new dataset and a pre-trained model, what properties of the dataset make it few-shot learnable, and are these properties independent of the specific adaptation techniques used? We consider an extensive set of recent few-shot learning methods and show that their performance across a large number of datasets is highly correlated, showing that few-shot hardness may be intrinsic to datasets, for a given pre-trained model. To estimate intrinsic few-shot hardness, we then propose a simple and lightweight metric called Spread that captures the intuition that few-shot learning is made possible by exploiting feature-space invariances between training and test samples. Our metric better accounts for few-shot hardness compared to existing notions of hardness and is ~8-100x faster to compute.

Current approaches for fixing systematic problems in NLP models (e.g., regex patches, finetuning on more data) are either brittle, or labor-intensive and liable to shortcuts. In contrast, humans often provide corrections to each other through natural language. Taking inspiration from this, we explore natural language patches—declarative statements that allow developers to provide corrective feedback at the right level of abstraction, either overriding the model (“if a review gives 2 stars, the sentiment is negative”) or providing additional information the model may lack (“if something is described as the bomb, then it is good”). We model the task of determining if a patch applies separately from the task of integrating patch information, and show that with a small amount of synthetic data, we can teach models to effectively use real patches on real data—1 to 7 patches improve accuracy by ~1–4 accuracy points on different slices of a sentiment analysis dataset, and F1 by 7 points on a relation extraction dataset. Finally, we show that finetuning on as many as 100 labeled examples may be needed to match the performance of a small set of language patches.

Meta-learning promises few-shot learners that can adapt to new distributions by repurposing knowledge acquired from previous training. However, we believe meta-learning has not yet succeeded in NLP due to the lack of a well-defined task distribution, leading to attempts that treat datasets as tasks. Such an ad hoc task distribution causes problems of quantity and quality. Since there’s only a handful of datasets for any NLP problem, meta-learners tend to overfit their adaptation mechanism and, since NLP datasets are highly heterogeneous, many learning episodes have poor transfer between their support and query sets, which discourages the meta-learner from adapting. To alleviate these issues, we propose DReCA (Decomposing datasets into Reasoning Categories), a simple method for discovering and using latent reasoning categories in a dataset, to form additional high quality tasks. DReCA works by splitting examples into label groups, embedding them with a finetuned BERT model and then clustering each group into reasoning categories. Across four few-shot NLI problems, we demonstrate that using DReCA improves the accuracy of meta-learners by 1.5-4%

Suppose we want to specify the inductive bias that married couples typically go on honeymoons for the task of extracting pairs of spouses from text. In this paper, we allow model developers to specify these types of inductive biases as natural language explanations. We use BERT fine-tuned on MultiNLI to “interpret” these explanations with respect to the input sentence, producing explanation-guided representations of the input. Across three relation extraction tasks, our method, ExpBERT, matches a BERT baseline but with 3–20x less labeled data and improves on the baseline by 3–10 F1 points with the same amount of labeled data.

Training semantic parsers from question-answer pairs typically involves searching over an exponentially large space of logical forms, and an unguided search can easily be misled by spurious logical forms that coincidentally evaluate to the correct answer. We propose a novel iterative training algorithm that alternates between searching for consistent logical forms and maximizing the marginal likelihood of the retrieved ones. This training scheme lets us iteratively train models that provide guidance to subsequent ones to search for logical forms of increasing complexity, thus dealing with the problem of spuriousness. We evaluate these techniques on two hard datasets: WikiTableQuestions (WTQ) and Cornell Natural Language Visual Reasoning (NLVR), and show that our training algorithm outperforms the previous best systems, on WTQ in a comparable setting, and on NLVR with significantly less supervision.

Complex textual information extraction tasks are often posed as sequence labeling or shallow parsing, where fields are extracted using local labels made consistent through probabilistic inference in a graphical model with constrained transitions. Recently, it has become common to locally parametrize these models using rich features extracted by recurrent neural networks (such as LSTM), while enforcing consistent outputs through a simple linear-chain model, representing Markovian dependencies between successive labels. However, the simple graphical model structure belies the often complex non-local constraints between output labels. For example, many fields, such as a first name, can only occur a fixed number of times, or in the presence of other fields. While RNNs have provided increasingly powerful context-aware local features for sequence tagging, they have yet to be integrated with a global graphical model of similar expressivity in the output distribution. Our model goes beyond the linear chain CRF to incorporate multiple hidden states per output label, but parametrizes them parsimoniously with low-rank log-potential scoring matrices, effectively learning an embedding space for hidden states. This augmented latent space of inference variables complements the rich feature representation of the RNN, and allows exact global inference obeying complex, learned non-local output constraints. We experiment with several datasets and show that the model outperforms baseline CRF+RNN models when global output constraints are necessary at inference-time, and explore the interpretable latent structure.

Extraction from raw text to a knowledge base of entities and fine-grained types is often cast as prediction into a flat set of entity and type labels, neglecting the rich hierarchies over types and entities contained in curated ontologies. Previous attempts to incorporate hierarchical structure have yielded little benefit and are restricted to shallow ontologies. This paper presents new methods using real and complex bilinear mappings for integrating hierarchical information, yielding substantial improvement over flat predictions in entity linking and fine-grained entity typing, and achieving new state-of-the-art results for end-to-end models on the benchmark FIGER dataset. We also present two new human-annotated datasets containing wide and deep hierarchies which we will release to the community to encourage further research in this direction: MedMentions, a collection of PubMed abstracts in which 246k mentions have been mapped to the massive UMLS ontology; and TypeNet, which aligns Freebase types with the WordNet hierarchy to obtain nearly 2k entity types. In experiments on all three datasets we show substantial gains from hierarchy-aware training.

Embedding methods which enforce a partial order or lattice structure over the concept space, such as Order Embeddings (OE), are a natural way to model transitive relational data (e.g. entailment graphs). However, OE learns a deterministic knowledge base, limiting expressiveness of queries and the ability to use uncertainty for both prediction and learning (e.g. learning from expectations). Probabilistic extensions of OE have provided the ability to somewhat calibrate these denotational probabilities while retaining the consistency and inductive bias of ordered models, but lack the ability to model the negative correlations found in real-world knowledge. In this work we show that a broad class of models that assign probability measures to OE can never capture negative correlation, which motivates our construction of a novel box lattice and accompanying probability measure to capture anti-correlation and even disjoint concepts, while still providing the benefits of probabilistic modeling, such as the ability to perform rich joint and conditional queries over arbitrary sets of concepts, and both learning from and predicting calibrated uncertainty. We show improvements over previous approaches in modeling the Flickr and WordNet entailment graphs, and investigate the power of the model.