No more hard prompts: SoftSRV prompting for synthetic data generation

We present a novel soft prompt based framework, SoftSRV, that leverages a frozen pre-trained large language model (LLM) to generate targeted synthetic text sequences. Given a sample from the target distribution, our proposed framework uses data-driven loss minimization to train a parameterized "contextual" soft prompt. This soft prompt is then used to steer the frozen LLM to generate synthetic sequences that are similar to the target distribution. We argue that SoftSRV provides a practical improvement over common hard-prompting approaches that rely on human-curated prompt-templates, which can be idiosyncratic, labor-intensive to craft, and may need to be specialized per domain. We empirically evaluate SoftSRV and hard-prompting baselines by generating synthetic data to fine-tune a small Gemma model on three different domains (coding, math, reasoning). To stress the generality of SoftSRV, we perform these evaluations without any particular specialization of the framework to each domain. We find that SoftSRV significantly improves upon hard-prompting baselines, generating data with superior fine-tuning performance and that better matches the target distribution according to the MAUVE similarity metric.

Mimetic Initialization Helps State Space Models Learn to Recall

Recent work has shown that state space models such as Mamba are significantly worse than Transformers on recall-based tasks due to the fact that their state size is constant with respect to their input sequence length. But in practice, state space models have fairly large state sizes, and we conjecture that they should be able to perform much better at these tasks than previously reported. We investigate whether their poor copying and recall performance could be due in part to training difficulties rather than fundamental capacity constraints. Based on observations of their "attention" maps, we propose a structured initialization technique that allows state space layers to more readily mimic attention. Across a variety of architecture settings, our initialization makes it substantially easier for Mamba to learn to copy and do associative recall from scratch.

Can Looped Transformers Learn to Implement Multi-step Gradient Descent for In-context Learning?

The remarkable capability of Transformers to do reasoning and few-shot learning, without any fine-tuning, is widely conjectured to stem from their ability to implicitly simulate a multi-step algorithms -- such as gradient descent -- with their weights in a single forward pass. Recently, there has been progress in understanding this complex phenomenon from an expressivity point of view, by demonstrating that Transformers can express such multi-step algorithms. However, our knowledge about the more fundamental aspect of its learnability, beyond single layer models, is very limited. In particular, can training Transformers enable convergence to algorithmic solutions? In this work we resolve this for in-context linear regression with linear looped Transformers -- a multi-layer model with weight sharing that is conjectured to have an inductive bias to learn fix-point iterative algorithms. More specifically, for this setting we show that the global minimizer of the population training loss implements multi-step preconditioned gradient descent, with a preconditioner that adapts to the data distribution. Furthermore, we show a fast convergence for gradient flow on the regression loss, despite the non-convexity of the landscape, by proving a novel gradient dominance condition. To our knowledge, this is the first theoretical analysis for multi-layer Transformer in this setting. We further validate our theoretical findings through synthetic experiments.

On the Inductive Bias of Stacking Towards Improving Reasoning

Given the increasing scale of model sizes, novel training strategies like gradual stacking [Gong et al., 2019, Reddi et al., 2023] have garnered interest. Stacking enables efficient training by gradually growing the depth of a model in stages and using layers from a smaller model in an earlier stage to initialize the next stage. Although efficient for training, the model biases induced by such growing approaches are largely unexplored. In this work, we examine this fundamental aspect of gradual stacking, going beyond its efficiency benefits. We propose a variant of gradual stacking called MIDAS that can speed up language model training by up to 40%. Furthermore we discover an intriguing phenomenon: MIDAS is not only training-efficient but surprisingly also has an inductive bias towards improving downstream tasks, especially tasks that require reasoning abilities like reading comprehension and math problems, despite having similar or slightly worse perplexity compared to baseline training. To further analyze this inductive bias, we construct reasoning primitives -- simple synthetic tasks that are building blocks for reasoning -- and find that a model pretrained with stacking is significantly better than standard pretraining on these primitives, with and without fine-tuning. This provides stronger and more robust evidence for this inductive bias towards reasoning. These findings of training efficiency and inductive bias towards reasoning are verified at 1B, 2B and 8B parameter language models. Finally, we conjecture the underlying reason for this inductive bias by exploring the connection of stacking to looped models and provide strong supporting empirical analysis.

Promises and Pitfalls of Generative Masked Language Modeling: Theoretical Framework and Practical Guidelines

Autoregressive language models are the currently dominant paradigm for text generation, but they have some fundamental limitations that cannot be remedied by scale-for example inherently sequential and unidirectional generation. While alternate classes of models have been explored, we have limited mathematical understanding of their fundamental power and limitations. In this paper we focus on Generative Masked Language Models (GMLMs), a non-autoregressive paradigm in which we train a model to fit conditional probabilities of the data distribution via masking, which are subsequently used as inputs to a Markov Chain to draw samples from the model, These models empirically strike a promising speed-quality trade-off as each step can be typically parallelized by decoding the entire sequence in parallel. We develop a mathematical framework for analyzing and improving such models which sheds light on questions of sample complexity and inference speed and quality. Empirically, we adapt the T5 model for iteratively-refined parallel decoding, achieving 2-3x speedup in machine translation with minimal sacrifice in quality compared with autoregressive models. We run careful ablation experiments to give recommendations on key design choices, and make fine-grained observations on the common error modes in connection with our theory. Our mathematical analyses and empirical observations characterize both potentials and limitations of this approach, and can be applied to future works on improving understanding and performance of GMLMs. Our codes are released at https://github.com/google-research/google-research/tree/master/padir

Efficient Document Ranking with Learnable Late Interactions

Cross-Encoder (CE) and Dual-Encoder (DE) models are two fundamental approaches for query-document relevance in information retrieval. To predict relevance, CE models use joint query-document embeddings, while DE models maintain factorized query and document embeddings; usually, the former has higher quality while the latter benefits from lower latency. Recently, late-interaction models have been proposed to realize more favorable latency-quality tradeoffs, by using a DE structure followed by a lightweight scorer based on query and document token embeddings. However, these lightweight scorers are often hand-crafted, and there is no understanding of their approximation power; further, such scorers require access to individual document token embeddings, which imposes an increased latency and storage burden. In this paper, we propose novel learnable late-interaction models (LITE) that resolve these issues. Theoretically, we prove that LITE is a universal approximator of continuous scoring functions, even for relatively small embedding dimension. Empirically, LITE outperforms previous late-interaction models such as ColBERT on both in-domain and zero-shot re-ranking tasks. For instance, experiments on MS MARCO passage re-ranking show that LITE not only yields a model with better generalization, but also lowers latency and requires 0.25x storage compared to ColBERT.

Landscape-Aware Growing: The Power of a Little LAG

Recently, there has been increasing interest in efficient pretraining paradigms for training Transformer-based models. Several recent approaches use smaller models to initialize larger models in order to save computation (e.g., stacking and fusion). In this work, we study the fundamental question of how to select the best growing strategy from a given pool of growing strategies. Prior works have extensively focused on loss- and/or function-preserving behavior at initialization or simply performance at the end of training. Instead, we identify that behavior at initialization can be misleading as a predictor of final performance and present an alternative perspective based on early training dynamics, which we call "landscape-aware growing (LAG)". We perform extensive analysis of correlation of the final performance with performance in the initial steps of training and find early and more accurate predictions of the optimal growing strategy (i.e., with only a small "lag" after initialization). This perspective also motivates an adaptive strategy for gradual stacking.

Faster Cascades via Speculative Decoding

Cascades and speculative decoding are two common approaches to improving language models' inference efficiency. Both approaches involve interleaving models of different sizes, but via fundamentally distinct mechanisms: cascades employ a deferral rule that invokes the larger model only for "hard" inputs, while speculative decoding uses speculative execution to primarily invoke the larger model in parallel verification mode. These mechanisms offer different benefits: empirically, cascades are often capable of yielding better quality than even the larger model, while theoretically, speculative decoding offers a guarantee of quality-neutrality. In this paper, we leverage the best of both these approaches by designing new speculative cascading techniques that implement their deferral rule through speculative execution. We characterize the optimal deferral rule for our speculative cascades, and employ a plug-in approximation to the optimal rule. Through experiments with T5 models on benchmark language tasks, we show that the proposed approach yields better cost-quality trade-offs than cascading and speculative decoding baselines.

Language Model Cascades: Token-level uncertainty and beyond

Recent advances in language models (LMs) have led to significant improvements in quality on complex NLP tasks, but at the expense of increased inference costs. Cascading offers a simple strategy to achieve more favorable cost-quality tradeoffs: here, a small model is invoked for most "easy" instances, while a few "hard" instances are deferred to the large model. While the principles underpinning cascading are well-studied for classification tasks - with deferral based on predicted class uncertainty favored theoretically and practically - a similar understanding is lacking for generative LM tasks. In this work, we initiate a systematic study of deferral rules for LM cascades. We begin by examining the natural extension of predicted class uncertainty to generative LM tasks, namely, the predicted sequence uncertainty. We show that this measure suffers from the length bias problem, either over- or under-emphasizing outputs based on their lengths. This is because LMs produce a sequence of uncertainty values, one for each output token; and moreover, the number of output tokens is variable across examples. To mitigate this issue, we propose to exploit the richer token-level uncertainty information implicit in generative LMs. We argue that naive predicted sequence uncertainty corresponds to a simple aggregation of these uncertainties. By contrast, we show that incorporating token-level uncertainty through learned post-hoc deferral rules can significantly outperform such simple aggregation strategies, via experiments on a range of natural language benchmarks with FLAN-T5 models. We further show that incorporating embeddings from the smaller model and intermediate layers of the larger model can give an additional boost in the overall cost-quality tradeoff.

Towards Fast Inference: Exploring and Improving Blockwise Parallel Drafts

Despite the remarkable strides made by autoregressive language models, their potential is often hampered by the slow inference speeds inherent in sequential token generation. Blockwise parallel decoding (BPD) was proposed by Stern et al. (2018) as a way to improve inference speed of language models. In this paper, we make two contributions to understanding and improving BPD drafts. We first offer an analysis of the token distributions produced by the BPD prediction heads. Secondly, we use this analysis to inform algorithms to improve BPD inference speed by refining the BPD drafts using small n-gram or neural language models. We empirically show that these refined BPD drafts yield a higher average verified prefix length across tasks.