Moshe Wasserblat

Lewis Tunstall, Nils Reimers, Unso Eun Seo Jo et al. · huggingface

Recent few-shot methods, such as parameter-efficient fine-tuning (PEFT) and pattern exploiting training (PET), have achieved impressive results in label-scarce settings. However, they are difficult to employ since they are subject to high variability from manually crafted prompts, and typically require billion-parameter language models to achieve high accuracy. To address these shortcomings, we propose SetFit (Sentence Transformer Fine-tuning), an efficient and prompt-free framework for few-shot fine-tuning of Sentence Transformers (ST). SetFit works by first fine-tuning a pretrained ST on a small number of text pairs, in a contrastive Siamese manner. The resulting model is then used to generate rich text embeddings, which are used to train a classification head. This simple framework requires no prompts or verbalizers, and achieves high accuracy with orders of magnitude less parameters than existing techniques. Our experiments show that SetFit obtains comparable results with PEFT and PET techniques, while being an order of magnitude faster to train. We also show that SetFit can be applied in multilingual settings by simply switching the ST body. Our code is available at https://github.com/huggingface/setfit and our datasets at https://huggingface.co/setfit .

Daniel Fleischer, Moshe Berchansky, Moshe Wasserblat et al. · microsoft-research

Implementing Retrieval-Augmented Generation (RAG) systems is inherently complex, requiring deep understanding of data, use cases, and intricate design decisions. Additionally, evaluating these systems presents significant challenges, necessitating assessment of both retrieval accuracy and generative quality through a multi-faceted approach. We introduce RAG Foundry, an open-source framework for augmenting large language models for RAG use cases. RAG Foundry integrates data creation, training, inference and evaluation into a single workflow, facilitating the creation of data-augmented datasets for training and evaluating large language models in RAG settings. This integration enables rapid prototyping and experimentation with various RAG techniques, allowing users to easily generate datasets and train RAG models using internal or specialized knowledge sources. We demonstrate the framework effectiveness by augmenting and fine-tuning Llama-3 and Phi-3 models with diverse RAG configurations, showcasing consistent improvements across three knowledge-intensive datasets. Code is released as open-source in https://github.com/IntelLabs/RAGFoundry.

Moshe Berchansky, Peter Izsak, Avi Caciularu et al. · microsoft-research

Fusion-in-Decoder (FiD) is an effective retrieval-augmented language model applied across a variety of open-domain tasks, such as question answering, fact checking, etc. In FiD, supporting passages are first retrieved and then processed using a generative model (Reader), which can cause a significant bottleneck in decoding time, particularly with long outputs. In this work, we analyze the contribution and necessity of all the retrieved passages to the performance of reader models, and propose eliminating some of the retrieved information, at the token level, that might not contribute essential information to the answer generation process. We demonstrate that our method can reduce run-time by up to 62.2%, with only a 2% reduction in performance, and in some cases, even improve the performance results.

Haihao Shen, Hengyu Meng, Bo Dong et al. · mit

In recent years, Transformer-based language models have become the standard approach for natural language processing tasks. However, stringent throughput and latency requirements in industrial applications are limiting their adoption. To mitigate the gap, model compression techniques such as structured pruning are being used to improve inference efficiency. However, most existing neural network inference runtimes lack adequate support for structured sparsity. In this paper, we propose an efficient sparse deep learning inference software stack for Transformer-based language models where the weights are pruned with constant block size. Our sparse software accelerator leverages Intel Deep Learning Boost to maximize the performance of sparse matrix - dense matrix multiplication (commonly abbreviated as SpMM) on CPUs. Our SpMM kernel outperforms the existing sparse libraries (oneMKL, TVM, and LIBXSMM) by an order of magnitude on a wide range of GEMM shapes under 5 representative sparsity ratios (70%, 75%, 80%, 85%, 90%). Moreover, our SpMM kernel shows up to 5x speedup over dense GEMM kernel of oneDNN, a well-optimized dense library widely used in industry. We apply our sparse accelerator on widely-used Transformer-based language models including Bert-Mini, DistilBERT, Bert-Base, and BERT-Large. Our sparse inference software shows up to 1.5x speedup over Neural Magic's Deepsparse under same configurations on Xeon on Amazon Web Services under proxy production latency constraints. We also compare our solution with two framework-based inference solutions, ONNX Runtime and PyTorch, and demonstrate up to 37x speedup over ONNX Runtime and 345x over PyTorch on Xeon under the latency constraints. All the source code is publicly available on Github: https://github.com/intel/intel-extension-for-transformers.

Haihao Shen, Ofir Zafrir, Bo Dong et al. · mit

Transformer-based language models have become the standard approach to solving natural language processing tasks. However, industry adoption usually requires the maximum throughput to comply with certain latency constraints that prevents Transformer models from being used in production. To address this gap, model compression techniques such as quantization and pruning may be used to improve inference efficiency. However, these compression techniques require specialized software to apply and deploy at scale. In this work, we propose a new pipeline for creating and running Fast Transformer models on CPUs, utilizing hardware-aware pruning, knowledge distillation, quantization, and our own Transformer inference runtime engine with optimized kernels for sparse and quantized operators. We demonstrate the efficiency of our pipeline by creating a Fast DistilBERT model showing minimal accuracy loss on the question-answering SQuADv1.1 benchmark, and throughput results under typical production constraints and environments. Our results outperform existing state-of-the-art Neural Magic's DeepSparse runtime performance by up to 50% and up to 4.1x performance speedup over ONNX Runtime. Source code is publicly available at https://github.com/intel/intel-extension-for-transformers.

Jonathan Mamou, Oren Pereg, Moshe Wasserblat et al.

The remarkable success of large transformer-based models such as BERT, RoBERTa and XLNet in many NLP tasks comes with a large increase in monetary and environmental cost due to their high computational load and energy consumption. In order to reduce this computational load in inference time, we present TangoBERT, a cascaded model architecture in which instances are first processed by an efficient but less accurate first tier model, and only part of those instances are additionally processed by a less efficient but more accurate second tier model. The decision of whether to apply the second tier model is based on a confidence score produced by the first tier model. Our simple method has several appealing practical advantages compared to standard cascading approaches based on multi-layered transformer models. First, it enables higher speedup gains (average lower latency). Second, it takes advantage of batch size optimization for cascading, which increases the relative inference cost reductions. We report TangoBERT inference CPU speedup on four text classification GLUE tasks and on one reading comprehension task. Experimental results show that TangoBERT outperforms efficient early exit baseline models; on the the SST-2 task, it achieves an accuracy of 93.9% with a CPU speedup of 8.2x.

Phillip Howard, Arden Ma, Vasudev Lal et al.

The extraction of aspect terms is a critical step in fine-grained sentiment analysis of text. Existing approaches for this task have yielded impressive results when the training and testing data are from the same domain. However, these methods show a drastic decrease in performance when applied to cross-domain settings where the domain of the testing data differs from that of the training data. To address this lack of extensibility and robustness, we propose a novel approach for automatically constructing domain-specific knowledge graphs that contain information relevant to the identification of aspect terms. We introduce a methodology for injecting information from these knowledge graphs into Transformer models, including two alternative mechanisms for knowledge insertion: via query enrichment and via manipulation of attention patterns. We demonstrate state-of-the-art performance on benchmark datasets for cross-domain aspect term extraction using our approach and investigate how the amount of external knowledge available to the Transformer impacts model performance.

Shira Guskin, Moshe Wasserblat, Chang Wang et al.

Limited computational budgets often prevent transformers from being used in production and from having their high accuracy utilized. A knowledge distillation approach addresses the computational efficiency by self-distilling BERT into a smaller transformer representation having fewer layers and smaller internal embedding. However, the performance of these models drops as we reduce the number of layers, notably in advanced NLP tasks such as span question answering. In addition, a separate model must be trained for each inference scenario with its distinct computational budget. Dynamic-TinyBERT tackles both limitations by partially implementing the Length Adaptive Transformer (LAT) technique onto TinyBERT, achieving x3 speedup over BERT-base with minimal accuracy loss. In this work, we expand the Dynamic-TinyBERT approach to generate a much more highly efficient model. We use MiniLM distillation jointly with the LAT method, and we further enhance the efficiency by applying low-bit quantization. Our quantized length-adaptive MiniLM model (QuaLA-MiniLM) is trained only once, dynamically fits any inference scenario, and achieves an accuracy-efficiency trade-off superior to any other efficient approaches per any computational budget on the SQuAD1.1 dataset (up to x8.8 speedup with <1% accuracy loss). The code to reproduce this work is publicly available on Github.

Nadav Timor, Jonathan Mamou, Daniel Korat et al.

This paper introduces distributed speculative inference (DSI), a novel inference algorithm that is provably faster than speculative inference (SI) [leviathan2023, chen2023, miao2024, sun2025, timor2025] and standard autoregressive inference (non-SI). Like other SI algorithms, DSI operates on frozen language models (LMs), requiring no training or architectural modifications, and it preserves the target distribution. Prior studies on SI have demonstrated empirical speedups over non-SI--but rely on sufficiently fast and accurate drafters, which are often unavailable in practice. We identify a gap where SI can be slower than non-SI if drafters are too slow or inaccurate. We close this gap by proving that DSI is faster than both SI and non-SI--given any drafters. DSI is therefore not only faster than SI, but also unlocks the acceleration of LMs for which SI fails. DSI leverages speculation parallelism (SP), a novel type of task parallelism, to orchestrate target and drafter instances that overlap in time, establishing a new foundational tradeoff between computational resources and latency. Our simulations show that DSI is 1.29-1.92x faster than SI in single-node setups for various off-the-shelf LMs and tasks. We open-source all our code.

Daniel Fleischer, Moshe Berchansky, Gad Markovits et al.

In the rapidly evolving field of Natural Language Processing, Large Language Models (LLMs) are tasked with increasingly complex reasoning challenges. Traditional methods like chain-of-thought prompting have shown promise but often fall short in fully leveraging a model's reasoning capabilities. This paper introduces SQuARE (Sequential Question Answering Reasoning Engine), a novel prompting technique designed to improve reasoning through a self-interrogation paradigm. Building upon CoT frameworks, SQuARE prompts models to generate and resolve multiple auxiliary questions before tackling the main query, promoting a more thorough exploration of various aspects of a topic. Our expansive evaluations, conducted with Llama 3 and GPT-4o models across multiple question-answering datasets, demonstrate that SQuARE significantly surpasses traditional CoT prompts and existing rephrase-and-respond methods. By systematically decomposing queries, SQuARE advances LLM capabilities in reasoning tasks. The code is publicly available at https://github.com/IntelLabs/RAG-FiT/tree/square.

Shira Guskin, Moshe Wasserblat, Ke Ding et al.

Limited computational budgets often prevent transformers from being used in production and from having their high accuracy utilized. TinyBERT addresses the computational efficiency by self-distilling BERT into a smaller transformer representation having fewer layers and smaller internal embedding. However, TinyBERT's performance drops when we reduce the number of layers by 50%, and drops even more abruptly when we reduce the number of layers by 75% for advanced NLP tasks such as span question answering. Additionally, a separate model must be trained for each inference scenario with its distinct computational budget. In this work we present Dynamic-TinyBERT, a TinyBERT model that utilizes sequence-length reduction and Hyperparameter Optimization for enhanced inference efficiency per any computational budget. Dynamic-TinyBERT is trained only once, performing on-par with BERT and achieving an accuracy-speedup trade-off superior to any other efficient approaches (up to 3.3x with <1% loss-drop). Upon publication, the code to reproduce our work will be open-sourced.

Moshe Berchansky, Daniel Fleischer, Moshe Wasserblat et al. · microsoft-research

State-of-the-art performance in QA tasks is currently achieved by systems employing Large Language Models (LLMs), however these models tend to hallucinate information in their responses. One approach focuses on enhancing the generation process by incorporating attribution from the given input to the output. However, the challenge of identifying appropriate attributions and verifying their accuracy against a source is a complex task that requires significant improvements in assessing such systems. We introduce an attribution-oriented Chain-of-Thought reasoning method to enhance the accuracy of attributions. This approach focuses the reasoning process on generating an attribution-centric output. Evaluations on two context-enhanced question-answering datasets using GPT-4 demonstrate improved accuracy and correctness of attributions. In addition, the combination of our method with finetuning enhances the response and attribution accuracy of two smaller LLMs, showing their potential to outperform GPT-4 in some cases.

Nadav Timor, Jonathan Mamou, Daniel Korat et al.

Accelerating the inference of large language models (LLMs) is a critical challenge in generative AI. Speculative decoding (SD) methods offer substantial efficiency gains by generating multiple tokens using a single target forward pass. However, existing SD approaches require the drafter and target models to share the same vocabulary, thus limiting the pool of possible drafters, often necessitating the training of a drafter from scratch. We present three new SD methods that remove this shared-vocabulary constraint. All three methods preserve the target distribution (i.e., they are lossless) and work with off-the-shelf models without requiring additional training or modifications. Empirically, on summarization, programming, and long-context tasks, our algorithms demonstrate significant speedups of up to 2.8x over standard autoregressive decoding. By enabling any off-the-shelf model to serve as a drafter and requiring no retraining, this work substantially broadens the applicability of the SD framework in practice.

Jonathan Mamou, Oren Pereg, Daniel Korat et al.

Speculative decoding is commonly used for reducing the inference latency of large language models. Its effectiveness depends highly on the speculation lookahead (SL)-the number of tokens generated by the draft model at each iteration. In this work we show that the common practice of using the same SL for all iterations (static SL) is suboptimal. We introduce DISCO (DynamIc SpeCulation lookahead Optimization), a novel method for dynamically selecting the SL. Our experiments with four datasets show that DISCO reaches an average speedup of 10% compared to the best static SL baseline, while generating the exact same text.

Ofir Zafrir, Ariel Larey, Guy Boudoukh et al.

Transformer-based language models are applied to a wide range of applications in natural language processing. However, they are inefficient and difficult to deploy. In recent years, many compression algorithms have been proposed to increase the implementation efficiency of large Transformer-based models on target hardware. In this work we present a new method for training sparse pre-trained Transformer language models by integrating weight pruning and model distillation. These sparse pre-trained models can be used to transfer learning for a wide range of tasks while maintaining their sparsity pattern. We demonstrate our method with three known architectures to create sparse pre-trained BERT-Base, BERT-Large and DistilBERT. We show how the compressed sparse pre-trained models we trained transfer their knowledge to five different downstream natural language tasks with minimal accuracy loss. Moreover, we show how to further compress the sparse models' weights to 8bit precision using quantization-aware training. For example, with our sparse pre-trained BERT-Large fine-tuned on SQuADv1.1 and quantized to 8bit we achieve a compression ratio of $40$X for the encoder with less than $1\%$ accuracy loss. To the best of our knowledge, our results show the best compression-to-accuracy ratio for BERT-Base, BERT-Large, and DistilBERT.

Peter Izsak, Shira Guskin, Moshe Wasserblat

Training models on low-resource named entity recognition tasks has been shown to be a challenge, especially in industrial applications where deploying updated models is a continuous effort and crucial for business operations. In such cases there is often an abundance of unlabeled data, while labeled data is scarce or unavailable. Pre-trained language models trained to extract contextual features from text were shown to improve many natural language processing (NLP) tasks, including scarcely labeled tasks, by leveraging transfer learning. However, such models impose a heavy memory and computational burden, making it a challenge to train and deploy such models for inference use. In this work-in-progress we combined the effectiveness of transfer learning provided by pre-trained masked language models with a semi-supervised approach to train a fast and compact model using labeled and unlabeled examples. Preliminary evaluations show that the compact models can achieve competitive accuracy with 36x compression rate when compared with a state-of-the-art pre-trained language model, and run significantly faster in inference, allowing deployment of such models in production environments or on edge devices.

Ofir Zafrir, Guy Boudoukh, Peter Izsak et al.

Recently, pre-trained Transformer based language models such as BERT and GPT, have shown great improvement in many Natural Language Processing (NLP) tasks. However, these models contain a large amount of parameters. The emergence of even larger and more accurate models such as GPT2 and Megatron, suggest a trend of large pre-trained Transformer models. However, using these large models in production environments is a complex task requiring a large amount of compute, memory and power resources. In this work we show how to perform quantization-aware training during the fine-tuning phase of BERT in order to compress BERT by $4\times$ with minimal accuracy loss. Furthermore, the produced quantized model can accelerate inference speed if it is optimized for 8bit Integer supporting hardware.

Oren Pereg, Daniel Korat, Moshe Wasserblat et al.

We present ABSApp, a portable system for weakly-supervised aspect-based sentiment extraction. The system is interpretable and user friendly and does not require labeled training data, hence can be rapidly and cost-effectively used across different domains in applied setups. The system flow includes three stages: First, it generates domain-specific aspect and opinion lexicons based on an unlabeled dataset; second, it enables the user to view and edit those lexicons (weak supervision); and finally, it enables the user to select an unlabeled target dataset from the same domain, classify it, and generate an aspect-based sentiment report. ABSApp has been successfully used in a number of real-life use cases, among them movie review analysis and convention impact analysis.

Jonathan Mamou, Oren Pereg, Moshe Wasserblat et al.

In this paper, we present a novel algorithm that combines multi-context term embeddings using a neural classifier and we test this approach on the use case of corpus-based term set expansion. In addition, we present a novel and unique dataset for intrinsic evaluation of corpus-based term set expansion algorithms. We show that, over this dataset, our algorithm provides up to 5 mean average precision points over the best baseline.

Jonathan Mamou, Oren Pereg, Moshe Wasserblat et al.

We present SetExpander, a corpus-based system for expanding a seed set of terms into amore complete set of terms that belong to the same semantic class. SetExpander implements an iterative end-to-end workflow. It enables users to easily select a seed set of terms, expand it, view the expanded set, validate it, re-expand the validated set and store it, thus simplifying the extraction of domain-specific fine-grained semantic classes.SetExpander has been used successfully in real-life use cases including integration into an automated recruitment system and an issues and defects resolution system. A video demo of SetExpander is available at https://drive.google.com/open?id=1e545bB87Autsch36DjnJHmq3HWfSd1Rv (some images were blurred for privacy reasons)

Jonathan Mamou, Oren Pereg, Moshe Wasserblat et al.

We present SetExpander, a corpus-based system for expanding a seed set of terms into a more complete set of terms that belong to the same semantic class. SetExpander implements an iterative end-to end workflow for term set expansion. It enables users to easily select a seed set of terms, expand it, view the expanded set, validate it, re-expand the validated set and store it, thus simplifying the extraction of domain-specific fine-grained semantic classes. SetExpander has been used for solving real-life use cases including integration in an automated recruitment system and an issues and defects resolution system. A video demo of SetExpander is available at https://drive.google.com/open?id=1e545bB87Autsch36DjnJHmq3HWfSd1Rv (some images were blurred for privacy reasons).