While the biases of language models in production are extensively documented, the biases of their guardrails have been neglected. This paper studies how contextual information about the user influences the likelihood of an LLM to refuse to execute a request. By generating user biographies that offer ideological and demographic information, we find a number of biases in guardrail sensitivity on GPT-3.5. Younger, female, and Asian-American personas are more likely to trigger a refusal guardrail when requesting censored or illegal information. Guardrails are also sycophantic, refusing to comply with requests for a political position the user is likely to disagree with. We find that certain identity groups and seemingly innocuous information, e.g., sports fandom, can elicit changes in guardrail sensitivity similar to direct statements of political ideology. For each demographic category and even for American football team fandom, we find that ChatGPT appears to infer a likely political ideology and modify guardrail behavior accordingly.

Parameter efficient finetuning methods like low-rank adaptation (LoRA) aim to reduce the computational costs of finetuning pretrained Language Models (LMs). Enabled by these low-rank settings, we propose an even more efficient optimization strategy: Fast Forward, a simple and effective approach to accelerate large segments of SGD training. In a Fast Forward stage, we repeat the most recent optimizer step until the loss stops improving on a tiny validation set. By alternating between regular optimization steps and Fast Forward stages, Fast Forward provides up to an 87% reduction in FLOPs over standard SGD with Adam. We validate Fast Forward by finetuning various models on different tasks and demonstrate that it speeds up training without compromising model performance. Additionally, we analyze when and how to apply Fast Forward.

Although modern neural networks often generalize to new combinations of familiar concepts, the conditions that enable such compositionality have long been an open question. In this work, we study the systematicity gap in visual question answering: the performance difference between reasoning on previously seen and unseen combinations of object attributes. To test, we introduce a novel diagnostic dataset, CLEVR-HOPE. We find that the systematicity gap is not reduced by increasing the quantity of training data, but is reduced by increasing the diversity of training data. In particular, our experiments suggest that the more distinct attribute type combinations are seen during training, the more systematic we can expect the resulting model to be.

Many NLP researchers are experiencing an existential crisis triggered by the astonishing success of ChatGPT and other systems based on large language models (LLMs). After such a disruptive change to our understanding of the field, what is left to do? Taking a historical lens, we look for guidance from the first era of LLMs, which began in 2005 with large n-gram models for machine translation (MT). We identify durable lessons from the first era, and more importantly, we identify evergreen problems where NLP researchers can continue to make meaningful contributions in areas where LLMs are ascendant. We argue that disparities in scale are transient and researchers can work to reduce them; that data, rather than hardware, is still a bottleneck for many applications; that meaningful realistic evaluation is still an open problem; and that there is still room for speculative approaches.

The rise of the term “mechanistic interpretability” has accompanied increasing interest in understanding neural models—particularly language models. However, this jargon has also led to a fair amount of confusion. So, what does it mean to be mechanistic? We describe four uses of the term in interpretability research. The most narrow technical definition requires a claim of causality, while a broader technical definition allows for any exploration of a model’s internals. However, the term also has a narrow cultural definition describing a cultural movement. To understand this semantic drift, we present a history of the NLP interpretability community and the formation of the separate, parallel mechanistic interpretability community. Finally, we discuss the broad cultural definition—encompassing the entire field of interpretability—and why the traditional NLP interpretability community has come to embrace it. We argue that the polysemy of “mechanistic” is the product of a critical divide within the interpretability community.

Most works on transformers trained with the Masked Language Modeling (MLM) objective use the original BERT model’s fixed masking rate of 15%. We propose to instead dynamically schedule the masking rate throughout training. We find that linearly decreasing the masking rate over the course of pretraining improves average GLUE accuracy by up to 0.46% and 0.25% in BERT-base and BERT-large, respectively, compared to fixed rate baselines. These gains come from exposure to both high and low masking rate regimes, providing benefits from both settings. Our results demonstrate that masking rate scheduling is a simple way to improve the quality of masked language models, achieving up to a 1.89x speedup in pretraining for BERT-base as well as a Pareto improvement for BERT-large.

Recombining known primitive concepts into larger novel combinations is a quintessentially human cognitive capability. Whether large neural models in NLP acquire this ability while learning from data is an open question. In this paper, we look at this problem from the perspective of formal languages. We use deterministic finite-state transducers to make an unbounded number of datasets with controllable properties governing compositionality. By randomly sampling over many transducers, we explore which of their properties (number of states, alphabet size, number of transitions etc.) contribute to learnability of a compositional relation by a neural network. In general, we find that the models either learn the relations completely or not at all. The key is transition coverage, setting a soft learnability limit at 400 examples per transition.

Probes are models devised to investigate the encoding of knowledge—e.g. syntactic structure—in contextual representations. Probes are often designed for simplicity, which has led to restrictions on probe design that may not allow for the full exploitation of the structure of encoded information; one such restriction is linearity. We examine the case of a structural probe (Hewitt and Manning, 2019), which aims to investigate the encoding of syntactic structure in contextual representations through learning only linear transformations. By observing that the structural probe learns a metric, we are able to kernelize it and develop a novel non-linear variant with an identical number of parameters. We test on 6 languages and find that the radial-basis function (RBF) kernel, in conjunction with regularization, achieves a statistically significant improvement over the baseline in all languages—implying that at least part of the syntactic knowledge is encoded non-linearly. We conclude by discussing how the RBF kernel resembles BERT’s self-attention layers and speculate that this resemblance leads to the RBF-based probe’s stronger performance.

Recent work in NLP shows that LSTM language models capture compositional structure in language data. In contrast to existing work, we consider the learning process that leads to compositional behavior. For a closer look at how an LSTM’s sequential representations are composed hierarchically, we present a related measure of Decompositional Interdependence (DI) between word meanings in an LSTM, based on their gate interactions. We support this measure with experiments on English language data, where DI is higher on pairs of words with lower syntactic distance. To explore the inductive biases that cause these compositional representations to arise during training, we conduct simple experiments on synthetic data. These synthetic experiments support a specific hypothesis about how hierarchical structures are discovered over the course of training: that LSTM constituent representations are learned bottom-up, relying on effective representations of their shorter children, rather than on learning the longer-range relations independently.

The question of how to probe contextual word representations in a way that is principled and useful has seen significant recent attention. In our contribution to this discussion, we argue, first, for a probe metric that reflects the trade-off between probe complexity and performance: the Pareto hypervolume. To measure complexity, we present a number of parametric and non-parametric metrics. Our experiments with such metrics show that probe’s performance curves often fail to align with widely accepted rankings between language representations (with, e.g., non-contextual representations outperforming contextual ones). These results lead us to argue, second, that common simplistic probe tasks such as POS labeling and dependency arc labeling, are inadequate to evaluate the properties encoded in contextual word representations. We propose full dependency parsing as an example probe task, and demonstrate it with the Pareto hypervolume. In support of our arguments, the results of this illustrative experiment conform closer to accepted rankings among contextual word representations.

Research has shown that neural models implicitly encode linguistic features, but there has been no research showing how these encodings arise as the models are trained. We present the first study on the learning dynamics of neural language models, using a simple and flexible analysis method called Singular Vector Canonical Correlation Analysis (SVCCA), which enables us to compare learned representations across time and across models, without the need to evaluate directly on annotated data. We probe the evolution of syntactic, semantic, and topic representations, finding, for example, that part-of-speech is learned earlier than topic; that recurrent layers become more similar to those of a tagger during training; and embedding layers less similar. Our results and methods could inform better learning algorithms for NLP models, possibly to incorporate linguistic information more effectively.

A glut of recent research shows that language models capture linguistic structure. Such work answers the question of whether a model represents linguistic structure. But how and when are these structures acquired? Rather than treating the training process itself as a black box, we investigate how representations of linguistic structure are learned over time. In particular, we demonstrate that different aspects of linguistic structure are learned at different rates, with part of speech tagging acquired early and global topic information learned continuously.