The rapid growth of Large Language Models (LLMs) has been a driving force in transforming various domains, reshaping the artificial general intelligence landscape. However, the increasing computational and memory demands of these models present substantial challenges, hindering both academic research and practical applications. To address these issues, a wide array of methods, including both algorithmic and hardware solutions, have been developed to enhance the efficiency of LLMs. This survey delivers a comprehensive review of algorithmic advancements aimed at improving LLM efficiency. Unlike other surveys that typically focus on specific areas such as training or model compression, this paper examines the multi-faceted dimensions of efficiency essential for the end-to-end algorithmic development of LLMs. Specifically, it covers various topics related to efficiency, including scaling laws, data utilization, architectural innovations, training and tuning strategies, and inference techniques. This paper aims to serve as a valuable resource for researchers and practitioners, laying the groundwork for future innovations in this critical research area. Our repository of relevant references is maintained at url{https://github.com/tding1/Efficient-LLM-Survey}.

The current paradigm of large-scale pre-training and fine-tuning Transformer large language models has lead to significant improvements across the board in natural language processing. However, such large models are susceptible to overfitting to their training data, and as a result the models perform poorly when the domain changes. Also, due to the model's scale, the cost of fine-tuning the model to the new domain is large. Nonparametric Variational Information Bottleneck (NVIB) has been proposed as a regulariser for training cross-attention in Transformers, potentially addressing the overfitting problem. We extend the NVIB framework to replace all types of attention functions in Transformers, and show that existing pretrained Transformers can be reinterpreted as Nonparametric Variational (NV) models using a proposed identity initialisation. We then show that changing the initialisation introduces a novel, information-theoretic post-training regularisation in the attention mechanism, which improves out-of-domain generalisation without any training. This success supports the hypothesis that pretrained Transformers are implicitly NV Bayesian models.

Instruction-tuning is a widely adopted method of finetuning that enables large language models (LLMs) to generate output that more closely resembles human responses to natural language queries, in many cases leading to human-level performance on diverse testbeds. However, it remains unclear whether instruction-tuning truly makes LLMs more similar to how humans process language. We investigate the effect of instruction-tuning on LLM-human similarity in two ways: (1) brain alignment, the similarity of LLM internal representations to neural activity in the human language system, and (2) behavioral alignment, the similarity of LLM and human behavior on a reading task. We assess 25 vanilla and instruction-tuned LLMs across three datasets involving humans reading naturalistic stories and sentences. We discover that instruction-tuning generally enhances brain alignment by an average of 6%, but does not have a similar effect on behavioral alignment. To identify the factors underlying LLM-brain alignment, we compute correlations between the brain alignment of LLMs and various model properties, such as model size, various problem-solving abilities, and performance on tasks requiring world knowledge spanning various domains. Notably, we find a strong positive correlation between brain alignment and model size (r = 0.95), as well as performance on tasks requiring world knowledge (r = 0.81). Our results demonstrate that instruction-tuning LLMs improves both world knowledge representations and brain alignment, suggesting that mechanisms that encode world knowledge in LLMs also improve representational alignment to the human brain.

Developing the required technology to assist medical experts in their everyday activities is currently a hot topic in the Artificial Intelligence research field. Thus, a number of large language models (LLMs) and automated benchmarks have recently been proposed with the aim of facilitating information extraction in Evidence-Based Medicine (EBM) using natural language as a tool for mediating in human-AI interaction. The most representative benchmarks are limited to either multiple-choice or long-form answers and are available only in English. In order to address these shortcomings, in this paper we present a new dataset which, unlike previous work: (i) includes not only explanatory arguments for the correct answer, but also arguments to reason why the incorrect answers are not correct; (ii) the explanations are written originally by medical doctors to answer questions from the Spanish Residency Medical Exams. Furthermore, this new benchmark allows us to setup a novel extractive task which consists of identifying the explanation of the correct answer written by medical doctors. An additional benefit of our setting is that we can leverage the extractive QA paradigm to automatically evaluate performance of LLMs without resorting to costly manual evaluation by medical experts. Comprehensive experimentation with language models for Spanish shows that sometimes multilingual models fare better than monolingual ones, even outperforming models which have been adapted to the medical domain. Furthermore, results across the monolingual models are mixed, with supposedly smaller and inferior models performing competitively. In any case, the obtained results show that our novel dataset and approach can be an effective technique to help medical practitioners in identifying relevant evidence-based explanations for medical questions.

The evolution of legal datasets and the advent of large language models (LLMs) have significantly transformed the legal field, particularly in the generation of case judgment summaries. However, a critical concern arises regarding the potential biases embedded within these summaries. This study scrutinizes the biases present in case judgment summaries produced by legal datasets and large language models. The research aims to analyze the impact of biases on legal decision making. By interrogating the accuracy, fairness, and implications of biases in these summaries, this study contributes to a better understanding of the role of technology in legal contexts and the implications for justice systems worldwide. In this study, we investigate biases wrt Gender-related keywords, Race-related keywords, Keywords related to crime against women, Country names and religious keywords. The study shows interesting evidences of biases in the outputs generated by the large language models and pre-trained abstractive summarization models. The reasoning behind these biases needs further studies.

Neural metrics trained on human evaluations of MT tend to correlate well with human judgments, but their behavior is not fully understood. In this paper, we perform a controlled experiment and compare a baseline metric that has not been trained on human evaluations (Prism) to a trained version of the same metric (Prism+FT). Surprisingly, we find that Prism+FT becomes more robust to machine-translated references, which are a notorious problem in MT evaluation. This suggests that the effects of metric training go beyond the intended effect of improving overall correlation with human judgments.

A prompt is a sequence of symbol or tokens, selected from a vocabulary according to some rule, which is prepended/concatenated to a textual query. A key problem is how to select the sequence of tokens: in this paper we formulate it as a combinatorial optimization problem. The high dimensionality of the token space com-pounded by the length of the prompt sequence requires a very efficient solution. In this paper we propose a Bayesian optimization method, executed in a continuous em-bedding of the combinatorial space. In this paper we focus on hard prompt tuning (HPT) which directly searches for discrete tokens to be added to the text input with-out requiring access to the large language model (LLM) and can be used also when LLM is available only as a black-box. This is critically important if LLMs are made available in the Model as a Service (MaaS) manner as in GPT-4. The current manu-script is focused on the optimization of discrete prompts for classification tasks. The discrete prompts give rise to difficult combinatorial optimization problem which easily become intractable given the dimension of the token space in realistic applications. The optimization method considered in this paper is Bayesian optimization (BO) which has become the dominant approach in black-box optimization for its sample efficiency along with its modular structure and versatility. In this paper we use BoTorch, a library for Bayesian optimization research built on top of pyTorch. Albeit preliminary and obtained using a 'vanilla' version of BO, the experiments on RoB-ERTa on six benchmarks, show a good performance across a variety of tasks and enable an analysis of the tradeoff between size of the search space, accuracy and wall clock time.

Large language models (LLMs) are increasingly pivotal in a wide range of natural language processing tasks. Access to pre-trained models, courtesy of the open-source community, has made it possible to adapt these models to specific applications for enhanced performance. However, the substantial resources required for training these models necessitate efficient solutions. This paper introduces CoLLiE, an efficient library that facilitates collaborative training of large language models using 3D parallelism, parameter-efficient fine-tuning (PEFT) methods, and optimizers such as Lion, Adan, Sophia, LOMO and AdaLomo. With its modular design and comprehensive functionality, CoLLiE offers a balanced blend of efficiency, ease of use, and customization. CoLLiE has proven superior training efficiency in comparison with prevalent solutions in pre-training and fine-tuning scenarios. Furthermore, we provide an empirical evaluation of the correlation between model size and GPU memory consumption under different optimization methods, as well as an analysis of the throughput. Lastly, we carry out a comprehensive comparison of various optimizers and PEFT methods within the instruction-tuning context. CoLLiE is available at https://github.com/OpenLMLab/collie.

Deploying Large Language Models (LLMs) locally on mobile devices presents a significant challenge due to their extensive memory requirements. In this paper, we introduce LinguaLinked, a system for decentralized, distributed LLM inference on mobile devices. LinguaLinked enables collaborative execution of the inference task across multiple trusted devices. LinguaLinked ensures data privacy by processing information locally. LinguaLinked uses three key strategies. First, an optimized model assignment technique segments LLMs and uses linear optimization to align segments with each device's capabilities. Second, an optimized data transmission mechanism ensures efficient and structured data flow between model segments while also maintaining the integrity of the original model structure. Finally, LinguaLinked incorporates a runtime load balancer that actively monitors and redistributes tasks among mobile devices to prevent bottlenecks, enhancing the system's overall efficiency and responsiveness. We demonstrate that LinguaLinked facilitates efficient LLM inference while maintaining consistent throughput and minimal latency through extensive testing across various mobile devices, from high-end to low-end Android devices. In our evaluations, compared to the baseline, LinguaLinked achieves an inference performance acceleration of $1.11\times$ to $1.61\times$ in single-threaded settings, $1.73\times$ to $2.65\times$ with multi-threading. Additionally, runtime load balancing yields an overall inference acceleration of $1.29\times$ to $1.32\times$.

This paper examines the capacity of LLMs to reason with knowledge graphs using their internal knowledge graph, i.e., the knowledge graph they learned during pre-training. Two research questions are formulated to investigate the accuracy of LLMs in recalling information from pre-training knowledge graphs and their ability to infer knowledge graph relations from context. To address these questions, we employ LLMs to perform four distinct knowledge graph reasoning tasks. Furthermore, we identify two types of hallucinations that may occur during knowledge reasoning with LLMs: content and ontology hallucination. Our experimental results demonstrate that LLMs can successfully tackle both simple and complex knowledge graph reasoning tasks from their own memory, as well as infer from input context.