Fiddler: CPU-GPU Orchestration for Fast Inference of Mixture-of-Experts Models

Large Language Models (LLMs) based on Mixture-of-Experts (MoE) architecture are showing promising performance on various tasks. However, running them on resource-constrained settings, where GPU memory resources are not abundant, is challenging due to huge model sizes. Existing systems that offload model weights to CPU memory suffer from the significant overhead of frequently moving data between CPU and GPU. In this paper, we propose Fiddler, a resource-efficient inference engine with CPU-GPU orchestration for MoE models. The key idea of Fiddler is to use the computation ability of the CPU to minimize the data movement between the CPU and GPU. Our evaluation shows that Fiddler can run the uncompressed Mixtral-8x7B model, which exceeds 90GB in parameters, to generate over $3$ tokens per second on a single GPU with 24GB memory, showing an order of magnitude improvement over existing methods. The code of Fiddler is publicly available at \url{https://github.com/efeslab/fiddler}

Paralinguistics-Enhanced Large Language Modeling of Spoken Dialogue

Large Language Models (LLMs) have demonstrated superior abilities in tasks such as chatting, reasoning, and question-answering. However, standard LLMs may ignore crucial paralinguistic information, such as sentiment, emotion, and speaking style, which are essential for achieving natural, human-like spoken conversation, especially when such information is conveyed by acoustic cues. We therefore propose Paralinguistics-enhanced Generative Pretrained Transformer (ParalinGPT), an LLM that utilizes text and speech modalities to better model the linguistic content and paralinguistic attributes of spoken dialogue. The model takes the conversational context of text, speech embeddings, and paralinguistic attributes as input prompts within a serialized multitasking multimodal framework. Specifically, our framework serializes tasks in the order of current paralinguistic attribute prediction, response paralinguistic attribute prediction, and response text generation with autoregressive conditioning. We utilize the Switchboard-1 corpus, including its sentiment labels as the paralinguistic attribute, as our spoken dialogue dataset. Experimental results indicate the proposed serialized multitasking method outperforms typical sequence classification techniques on current and response sentiment classification. Furthermore, leveraging conversational context and speech embeddings significantly improves both response text generation and sentiment prediction. Our proposed framework achieves relative improvements of 6.7%, 12.0%, and 3.5% in current sentiment accuracy, response sentiment accuracy, and response text BLEU score, respectively.

Towards ASR Robust Spoken Language Understanding Through In-Context Learning With Word Confusion Networks

In the realm of spoken language understanding (SLU), numerous natural language understanding (NLU) methodologies have been adapted by supplying large language models (LLMs) with transcribed speech instead of conventional written text. In real-world scenarios, prior to input into an LLM, an automated speech recognition (ASR) system generates an output transcript hypothesis, where inherent errors can degrade subsequent SLU tasks. Here we introduce a method that utilizes the ASR system's lattice output instead of relying solely on the top hypothesis, aiming to encapsulate speech ambiguities and enhance SLU outcomes. Our in-context learning experiments, covering spoken question answering and intent classification, underline the LLM's resilience to noisy speech transcripts with the help of word confusion networks from lattices, bridging the SLU performance gap between using the top ASR hypothesis and an oracle upper bound. Additionally, we delve into the LLM's robustness to varying ASR performance conditions and scrutinize the aspects of in-context learning which prove the most influential.

Perseus: Removing Energy Bloat from Large Model Training

Training large AI models on numerous GPUs consumes a massive amount of energy. We observe that not all energy consumed during training directly contributes to end-to-end training throughput, and a significant portion can be removed without slowing down training, which we call energy bloat. In this work, we identify two independent sources of energy bloat in large model training, intrinsic and extrinsic, and propose Perseus, a unified optimization framework that mitigates both. Perseus obtains the "iteration time-energy" Pareto frontier of any large model training job using an efficient iterative graph cut-based algorithm and schedules energy consumption of its forward and backward computations across time to remove intrinsic and extrinsic energy bloat. Evaluation on large models like GPT-3 and Bloom shows that Perseus reduces energy consumption of large model training by up to 30%, enabling savings otherwise unobtainable before.

Generative Speech Recognition Error Correction with Large Language Models and Task-Activating Prompting

We explore the ability of large language models (LLMs) to act as speech recognition post-processors that perform rescoring and error correction. Our first focus is on instruction prompting to let LLMs perform these task without fine-tuning, for which we evaluate different prompting schemes, both zero- and few-shot in-context learning, and a novel task activation prompting method that combines causal instructions and demonstration to increase its context windows. Next, we show that rescoring only by in-context learning with frozen LLMs achieves results that are competitive with rescoring by domain-tuned LMs, using a pretrained first-pass recognition system and rescoring output on two out-of-domain tasks (ATIS and WSJ). By combining prompting techniques with fine-tuning we achieve error rates below the N-best oracle level, showcasing the generalization power of the LLMs.

Discriminative Speech Recognition Rescoring with Pre-trained Language Models

Second pass rescoring is a critical component of competitive automatic speech recognition (ASR) systems. Large language models have demonstrated their ability in using pre-trained information for better rescoring of ASR hypothesis. Discriminative training, directly optimizing the minimum word-error-rate (MWER) criterion typically improves rescoring. In this study, we propose and explore several discriminative fine-tuning schemes for pre-trained LMs. We propose two architectures based on different pooling strategies of output embeddings and compare with probability based MWER. We conduct detailed comparisons between pre-trained causal and bidirectional LMs in discriminative settings. Experiments on LibriSpeech demonstrate that all MWER training schemes are beneficial, giving additional gains upto 8.5\% WER. Proposed pooling variants achieve lower latency while retaining most improvements. Finally, our study concludes that bidirectionality is better utilized with discriminative training.

Generative Speech Recognition Error Correction with Large Language Models

We explore the ability of large language models (LLMs) to act as ASR post-processors that perform rescoring and error correction. Our focus is on instruction prompting to let LLMs perform these task without fine-tuning, for which we evaluate different prompting schemes, both zero- and few-shot in-context learning, and a novel task-activating prompting (TAP) method that combines instruction and demonstration. Using a pre-trained first-pass system and rescoring output on two out-of-domain tasks (ATIS and WSJ), we show that rescoring only by in-context learning with frozen LLMs achieves results that are competitive with rescoring by domain-tuned LMs. By combining prompting techniques with fine-tuning we achieve error rates below the N-best oracle level, showcasing the generalization power of the LLMs.

Low-rank Adaptation of Large Language Model Rescoring for Parameter-Efficient Speech Recognition

We propose a neural language modeling system based on low-rank adaptation (LoRA) for speech recognition output rescoring. Although pretrained language models (LMs) like BERT have shown superior performance in second-pass rescoring, the high computational cost of scaling up the pretraining stage and adapting the pretrained models to specific domains limit their practical use in rescoring. Here we present a method based on low-rank decomposition to train a rescoring BERT model and adapt it to new domains using only a fraction (0.08%) of the pretrained parameters. These inserted matrices are optimized through a discriminative training objective along with a correlation-based regularization loss. The proposed low-rank adaptation Rescore-BERT (LoRB) architecture is evaluated on LibriSpeech and internal datasets with decreased training times by factors between 5.4 and 3.6.

Personalization for BERT-based Discriminative Speech Recognition Rescoring

Recognition of personalized content remains a challenge in end-to-end speech recognition. We explore three novel approaches that use personalized content in a neural rescoring step to improve recognition: gazetteers, prompting, and a cross-attention based encoder-decoder model. We use internal de-identified en-US data from interactions with a virtual voice assistant supplemented with personalized named entities to compare these approaches. On a test set with personalized named entities, we show that each of these approaches improves word error rate by over 10%, against a neural rescoring baseline. We also show that on this test set, natural language prompts can improve word error rate by 7% without any training and with a marginal loss in generalization. Overall, gazetteers were found to perform the best with a 10% improvement in word error rate (WER), while also improving WER on a general test set by 1%.