Mechanisms of Symbol Processing for In-Context Learning in Transformer Networks

Large Language Models (LLMs) have demonstrated impressive abilities in symbol processing through in-context learning (ICL). This success flies in the face of decades of predictions that artificial neural networks cannot master abstract symbol manipulation. We seek to understand the mechanisms that can enable robust symbol processing in transformer networks, illuminating both the unanticipated success, and the significant limitations, of transformers in symbol processing. Borrowing insights from symbolic AI on the power of Production System architectures, we develop a high-level language, PSL, that allows us to write symbolic programs to do complex, abstract symbol processing, and create compilers that precisely implement PSL programs in transformer networks which are, by construction, 100% mechanistically interpretable. We demonstrate that PSL is Turing Universal, so the work can inform the understanding of transformer ICL in general. The type of transformer architecture that we compile from PSL programs suggests a number of paths for enhancing transformers' capabilities at symbol processing. (Note: The first section of the paper gives an extended synopsis of the entire paper.)

Banyan: Improved Representation Learning with Explicit Structure

We present Banyan, an improved model to learn semantic representations by inducing explicit structure over data. In contrast to prior approaches using structure spanning single sentences, Banyan learns by resolving multiple constituent structures into a shared one explicitly incorporating global context. Combined with an improved message-passing scheme inspired by Griffin, Banyan learns significantly better representations, avoids spurious false negatives with contrastive learning, and drastically improves memory efficiency in such explicit-structured models. Using the Self-StrAE framework, we show that Banyan (a) outperforms baselines using sentential structure across various settings (b) matches or outperforms unstructured baselines like GloVe (+augmentations) and a RoBERTa medium (+simcse) pre-trained on 100M tokens, despite having just a handful of (non-embedding) parameters, and (c) also learns effective representations across several low resource (Asian and African) languages as measured on SemRel tasks.

Self-StrAE at SemEval-2024 Task 1: Making Self-Structuring AutoEncoders Learn More With Less

This paper presents two simple improvements to the Self-Structuring AutoEncoder (Self-StrAE). Firstly, we show that including reconstruction to the vocabulary as an auxiliary objective improves representation quality. Secondly, we demonstrate that increasing the number of independent channels leads to significant improvements in embedding quality, while simultaneously reducing the number of parameters. Surprisingly, we demonstrate that this trend can be followed to the extreme, even to point of reducing the total number of non-embedding parameters to seven. Our system can be pre-trained from scratch with as little as 10M tokens of input data, and proves effective across English, Spanish and Afrikaans.

On the effect of curriculum learning with developmental data for grammar acquisition

This work explores the degree to which grammar acquisition is driven by language `simplicity' and the source modality (speech vs. text) of data. Using BabyBERTa as a probe, we find that grammar acquisition is largely driven by exposure to speech data, and in particular through exposure to two of the BabyLM training corpora: AO-Childes and Open Subtitles. We arrive at this finding by examining various ways of presenting input data to our model. First, we assess the impact of various sequence-level complexity based curricula. We then examine the impact of learning over `blocks' -- covering spans of text that are balanced for the number of tokens in each of the source corpora (rather than number of lines). Finally, we explore curricula that vary the degree to which the model is exposed to different corpora. In all cases, we find that over-exposure to AO-Childes and Open Subtitles significantly drives performance. We verify these findings through a comparable control dataset in which exposure to these corpora, and speech more generally, is limited by design. Our findings indicate that it is not the proportion of tokens occupied by high-utility data that aids acquisition, but rather the proportion of training steps assigned to such data. We hope this encourages future research into the use of more developmentally plausible linguistic data (which tends to be more scarce) to augment general purpose pre-training regimes.

StrAE: Autoencoding for Pre-Trained Embeddings using Explicit Structure

This work explores the utility of explicit structure for representation learning in NLP by developing StrAE -- an autoencoding framework that faithfully leverages sentence structure to learn multi-level node embeddings in an unsupervised fashion. We use StrAE to train models across different types of sentential structure and objectives, including a novel contrastive loss over structure, and evaluate the learnt embeddings on a series of both intrinsic and extrinsic tasks. Our experiments indicate that leveraging explicit structure through StrAE leads to improved embeddings over prior work, and that our novel contrastive objective over structure outperforms the standard cross-entropy objective. Moreover, in contrast to findings from prior work that weakly leverages structure, we find that being completely faithful to structure does enable disambiguation between types of structure based on the corresponding model's performance. As further evidence of StrAE's utility, we develop a simple proof-of-concept approach to simultaneously induce structure while learning embeddings, rather than being given structure, and find that performance is comparable to that of the best-performing models where structure is given. Finally, we contextualise these results by comparing StrAE against standard unstructured baselines learnt in similar settings, and show that faithfully leveraging explicit structure can be beneficial in lexical and sentence-level semantics.