大模型基准

Large Language Models (LLMs) have the potential to transform humanities and social science research, yet their history knowledge and comprehension at a graduate level remains untested. Benchmarking LLMs in history is particularly challenging, given that human knowledge of history is inherently unbalanced, with more information available on Western history and recent periods. We introduce the History Seshat Test for LLMs (HiST-LLM), based on a subset of the Seshat Global History Databank, which provides a structured representation of human historical knowledge, containing 36,000 data points across 600 historical societies and over 2,700 scholarly references. This dataset covers every major world region from the Neolithic period to the Industrial Revolution and includes information reviewed and assembled by history experts and graduate research assistants. Using this dataset, we benchmark a total of seven models from the Gemini, OpenAI, and Llama families. We find that, in a four-choice format, LLMs have a balanced accuracy ranging from 33.6% (Llama-3.1-8B) to 46% (GPT-4-Turbo), outperforming random guessing (25%) but falling short of expert comprehension. LLMs perform better on earlier historical periods. Regionally, performance is more even but still better for the Americas and lowest in Oceania and Sub-Saharan Africa for the more advanced models. Our benchmark shows that while LLMs possess some expert-level historical knowledge, there is considerable room for improvement.

As Large Language Models (LLMs) demonstrate extensive capability in learning from documents, LLM unlearning becomes an increasingly important research area to address concerns of LLMs in terms of privacy, copyright, etc. A conventional LLM unlearning task typically involves two goals: (1) The target LLM should forget the knowledge in the specified forget documents; and (2) it should retain the other knowledge that the LLM possesses, for which we assume access to a small number of retain documents. To achieve both goals, a mainstream class of LLM unlearning methods introduces an optimization framework with a combination of two objectives – maximizing the prediction loss on the forget documents while minimizing that on the retain documents, which suffers from two challenges, degenerated output and catastrophic forgetting. In this paper, we propose a novel unlearning framework called Unlearning from Logit Difference (ULD), which introduces an assistant LLM that aims to achieve the opposite of the unlearning goals: remembering the forget documents and forgetting the retain knowledge. ULD then derives the unlearned LLM by computing the logit difference between the target and the assistant LLMs. We show that such reversed objectives would naturally resolve both aforementioned challenges while significantly improving the training efficiency. Extensive experiments demonstrate that our method efficiently achieves the intended forgetting while preserving the LLM’s overall capabilities, reducing training time by more than threefold. Notably, our method loses 0% of model utility on the ToFU benchmark, whereas baseline methods may sacrifice 17% of utility on average to achieve comparable forget quality.

Large Language Models (LLMs) have seen an impressive wave of advances, with models now excelling in a variety of tasks, such as mathematical reasoning and program synthesis. However, their potential to effectively use tools via API calls remains unfulfilled. This is a challenging task even for today’s state-of-the-art LLMs such as GPT-4 largely due to their unawareness of what APIs are available and how to use them in a frequently updated tool set. We develop Gorilla, a finetuned LLaMA model that surpasses the performance of GPT-4 on writing API calls. Trained with the novel Retriever Aware Training (RAT), when combined with a document retriever, Gorilla demonstrates a strong capability to adapt to test-time document changes, allowing flexible user updates or version changes. It also substantially mitigates the issue of hallucination, commonly encountered when prompting LLMs directly. To evaluate the model’s ability, we introduce APIBench, a comprehensive dataset consisting of HuggingFace, TorchHub, and TensorHub APIs. The successful integration of the retrieval system with Gorilla demonstrates the potential for LLMs to use tools more accurately, keep up with frequently updated documentation, and consequently increase the reliability and applicability of their outputs. Gorilla’s code, model, data, and demo are available at: https://gorilla.cs.berkeley.edu

Workplace meetings are vital to organizational collaboration, yet a large percentage of meetings are rated as ineffective. To help improve meeting effectiveness by understanding if the conversation is on topic, we create a comprehensive Topic-Conversation Relevance (TCR) dataset that covers a variety of domains and meeting styles. The TCR dataset includes 1,500 unique meetings, 22 million words in transcripts, and over 15,000 meeting topics, sourced from both newly collected Speech Interruption Meeting (SIM) data and existing public datasets. Along with the text data, we also open source scripts to generate synthetic meetings or create augmented meetings from the TCR dataset to enhance data diversity. For each data source, benchmarks are created using GPT-4 to evaluate the model accuracy in understanding transcription-topic relevance.

When reading long-form text, human cognition is complex and structurized. While large language models (LLMs) process input contexts through a causal and sequential perspective, this approach can potentially limit their ability to handle intricate and complex inputs effectively. To enhance LLM’s cognition capability, this paper presents a novel concept of context structurization. Specifically, we transform the plain, unordered contextual sentences into well-ordered and hierarchically structurized elements. By doing so, LLMs can better grasp intricate and extended contexts through precise attention and information-seeking along the organized structures. Extensive evaluations are conducted across various model architectures and sizes (including a series of auto-regressive LLMs as well as BERT-like masking models) on a diverse set of NLP tasks (e.g., context-based question-answering, exhaustive hallucination evaluation, and passage-level dense retrieval). Empirical results show consistent and significant performance gains afforded by a single-round structurization. In particular, we boost the open-sourced LLaMA2-70B model to achieve comparable performance against GPT-3.5-Turbo as the halluci- nation evaluator. Besides, we show the feasibility of distilling advanced LLMs’ language processing abilities to a smaller yet effective StruXGPT-7B to execute structurization, addressing the practicality of our approach. Code is available at https://github.com/alibaba/struxgpt.

The remarkable capabilities and easy accessibility of large language models (LLMs) have significantly increased societal risks (e.g., fake news generation), necessitating the development of LLM-generated text (LGT) detection methods for safe usage. However, detecting LGTs is challenging due to the vast number of LLMs, making it impractical to account for each LLM individually; hence, it is crucial to identify the common characteristics shared by these models. In this paper, we draw attention to a common feature of recent powerful LLMs, namely the alignment training, i.e., training LLMs to generate human-preferable texts. Our key finding is that as these aligned LLMs are trained to maximize the human preferences, they generate texts with higher estimated preferences even than human-written texts; thus, such texts are easily detected by using the reward model (i.e., an LLM trained to model human preference distribution). Based on this finding, we propose two training schemes to further improve the detection ability of the reward model, namely (i) continual preference fine-tuning to make reward model prefer aligned LGTs even further and (ii) reward modeling of Human/LLM mixed texts (a rephrased texts from human-written texts using aligned LLMs), which serves as a median preference text corpus between LGTs and human-written texts to learn the decision boundary better. We provide an extensive evaluation by considering six text domains across twelve aligned LLMs, where our method demonstrates state-of-the-art results.

Introduced to enhance the efficiency of large language model (LLM) inference, speculative decoding operates by having a smaller model generate a draft. A larger target model then reviews this draft to align with its output, and any acceptance by the target model results in a reduction of the number of the target model runs, ultimately improving efficiency. However, the drafting process in speculative decoding includes slow autoregressive generation and allocates equal time to generating tokens, irrespective of their importance. These inefficiencies collectively contribute to the suboptimal performance of speculative decoding. To further improve LLM inference, we introduce Cascade Speculative Drafting (CS Drafting), a speculative execution algorithm that incorporates two types of cascades. The *Vertical Cascade* eliminates autoregressive generation from neural models, while the *Horizontal Cascade* optimizes time allocation in drafting for improved efficiency. Combining both cascades, CS Drafting achieves greater speedup compared to the baselines in our experiments, while preserving the same output distribution as the target model. Our code is publicly available at https://github.com/lfsszd/CS-Drafting.

We explore uncertainty quantification in large language models (LLMs), with the goal to identify when uncertainty in responses given a query is large. We simultaneously consider both epistemic and aleatoric uncertainties, where the former comes from the lack of knowledge about the ground truth (such as about facts or the language), and the latter comes from irreducible randomness (such as multiple possible answers). In particular, we derive an information-theoretic metric that allows to reliably detect when only epistemic uncertainty is large, in which case the output of the model is unreliable. This condition can be computed based solely on the output of the model obtained simply by some special iterative prompting based on the previous responses. Such quantification, for instance, allows to detect hallucinations (cases when epistemic uncertainty is high) in both single- and multi-answer responses. This is in contrast to many standard uncertainty quantification strategies (such as thresholding the log-likelihood of a response) where hallucinations in the multi-answer case cannot be detected. We conduct a series of experiments which demonstrate the advantage of our formulation. Further, our investigations shed some light on how the probabilities assigned to a given output by an LLM can be amplified by iterative prompting, which might be of independent interest.

Language models (LMs) derive their capabilities from extensive training on diverse data, including copyrighted material. These models can memorize and generate content similar to their training data, potentially risking legal issues like copyright infringement. Therefore, model creators are motivated to develop mitigation methods that prevent generating particular copyrighted content, an ability we refer to as *copyright takedowns*. This paper introduces the first evaluation of the feasibility and side effects of copyright takedowns for LMs. We propose CoTaEval, an evaluation framework to assess the effectiveness of copyright takedown methods, the impact on the model's ability to retain uncopyrightable factual knowledge from the copyrighted content, and how well the model maintains its general utility and efficiency. We examine several strategies, including adding system prompts, decoding-time filtering interventions, and unlearning approaches. Our findings indicate that no method excels across all metrics, showing significant room for research in this unique problem setting and indicating potential unresolved challenges for live policy proposals.

Large Language Models (LLMs) have achieved remarkable success in various natural language processing tasks, including language modeling, understanding, and generation. However, the increased memory and computational costs associated with these models pose significant challenges for deployment on resource-limited devices. Structural pruning has emerged as a promising solution to reduce the costs of LLMs without requiring post-processing steps. Prior structural pruning methods either follow the dependence of structures at the cost of limiting flexibility, or introduce non-trivial additional parameters by incorporating different projection matrices. In this work, we propose a novel approach that relaxes the constraint imposed by regular structural pruning methods and eliminates the structural dependence along the embedding dimension. Our dimension-independent structural pruning method offers several benefits. Firstly, our method enables different blocks to utilize different subsets of the feature maps. Secondly, by removing structural dependence, we facilitate each block to possess varying widths along its input and output dimensions, thereby significantly enhancing the flexibility of structural pruning. We evaluate our method on various LLMs, including OPT, LLaMA, LLaMA-2, Phi-1.5, and Phi-2. Experimental results demonstrate that our approach outperforms other state-of-the-art methods, showing for the first time that structural pruning can achieve an accuracy similar to semi-structural pruning.

Discharge summaries in Electronic Health Records (EHRs) are crucial for clinical decision-making, but their length and complexity make information extraction challenging, especially when dealing with accumulated summaries across multiple patient admissions. Large Language Models (LLMs) show promise in addressing this challenge by efficiently analyzing vast and complex data. Existing benchmarks, however, fall short in properly evaluating LLMs' capabilities in this context, as they typically focus on single-note information or limited topics, failing to reflect the real-world inquiries required by clinicians. To bridge this gap, we introduce EHRNoteQA, a novel benchmark built on the MIMIC-IV EHR, comprising 962 different QA pairs each linked to distinct patients' discharge summaries. Every QA pair is initially generated using GPT-4 and then manually reviewed and refined by three clinicians to ensure clinical relevance. EHRNoteQA includes questions that require information across multiple discharge summaries and covers eight diverse topics, mirroring the complexity and diversity of real clinical inquiries. We offer EHRNoteQA in two formats: open-ended and multi-choice question answering, and propose a reliable evaluation method for each. We evaluate 27 LLMs using EHRNoteQA and examine various factors affecting the model performance (e.g., the length and number of discharge summaries). Furthermore, to validate EHRNoteQA as a reliable proxy for expert evaluations in clinical practice, we measure the correlation between the LLM performance on EHRNoteQA, and the LLM performance manually evaluated by clinicians. Results show that LLM performance on EHRNoteQA have higher correlation with clinician-evaluated performance (Spearman: 0.78, Kendall: 0.62) compared to other benchmarks, demonstrating its practical relevance in evaluating LLMs in clinical settings. EHRNoteQA will be publicly available to support further research and improve LLM evaluation in clinical practice. EHRNoteQA is publicly available under PhysioNet credential access at https://doi.org/10.13026/acga-ht95, and the code is available at https://github.com/ji-youn-kim/EHRNoteQA.

The long-tailed distribution is the underlying nature of real-world data, and it presents unprecedented challenges for training deep learning models. Existing long-tailed learning paradigms based on re-balancing or data augmentation have partially alleviated the long-tailed problem. However, they still have limitations, such as relying on manually designed augmentation strategies, having a limited search space, and using fixed augmentation strategies. To address these limitations, this paper proposes a novel LLM-based long-tailed data augmentation framework called LLM-AutoDA, which leverages large-scale pretrained models to automatically search for the optimal augmentation strategies suitable for long-tailed data distributions. In addition, it applies this strategy to the original imbalanced data to create an augmented dataset and fine-tune the underlying long-tailed learning model. The performance improvement on the validation set serves as a reward signal to update the generation model, enabling the generation of more effective augmentation strategies in the next iteration. We conducted extensive experiments on multiple mainstream long-tailed learning benchmarks. The results show that LLM-AutoDA outperforms state-of-the-art data augmentation methods and other re-balancing methods significantly.

Recent years have witnessed a clear trend towards language models with an ever-increasing number of parameters, as well as the growing training overhead and memory usage. Distributed training, particularly through Sharded Data Parallelism (ShardedDP) which partitions optimizer states among workers, has emerged as a crucial technique to mitigate training time and memory usage. Yet, a major challenge in the scalability of ShardedDP is the intensive communication of weights and gradients. While compression techniques can alleviate this issue, they often result in worse accuracy. Driven by this limitation, we propose SDP4Bit (Toward 4Bit Communication Quantization in Sharded Data Parallelism for LLM Training), which effectively reduces the communication of weights and gradients to nearly 4 bits via two novel techniques: quantization on weight differences, and two-level gradient smooth quantization. Furthermore, SDP4Bit presents an algorithm-system co-design with runtime optimization to minimize the computation overhead of compression. Additional to the theoretical guarantees of convergence, we empirically evaluate the accuracy of SDP4Bit on the pre-training of GPT models with up to 6.7 billion parameters, and the results demonstrate a negligible impact on training loss. Furthermore, speed experiments show that SDP4Bit achieves up to 4.08× speedup in end-to-end throughput on a scale of 128 GPUs.

As large language models gain widespread adoption, running them efficiently becomes a crucial task. Recent works on LLM inference use speculative decoding to achieve extreme speedups. However, most of these works implicitly design their algorithms for high-end datacenter hardware. In this work, we ask the opposite question: how fast can we run LLMs on consumer machines? Consumer GPUs can no longer fit the largest available models and must offload them to RAM or SSD. With parameter offloading, hundreds or thousands of tokens can be processed in batches within the same time as just one token, making it a natural fit for speculative decoding. We propose SpecExec (Speculative Execution), a simple parallel decoding method that can generate up to 20 tokens per target model iteration for popular LLM families. SpecExec takes the most probable continuations from the draft model to build a "cache" tree for the target model, which then gets validated in a single pass. Using SpecExec, we demonstrate inference of 50B+ parameter LLMs on consumer GPUs with RAM offloading at 4--6 tokens per second with 4-bit quantization or 2--3 tokens per second with 16-bit weights. Our code is available at https://github.com/yandex-research/specexec .

Quantization leverages lower-precision weights to reduce the memory usage of large language models (LLMs) and is a key technique for enabling their deployment on commodity hardware. While LLM quantization's impact on utility has been extensively explored, this work for the first time studies its adverse effects from a security perspective. We reveal that widely used quantization methods can be exploited to produce a harmful quantized LLM, even though the full-precision counterpart appears benign, potentially tricking users into deploying the malicious quantized model. We demonstrate this threat using a three-staged attack framework: (i) first, we obtain a malicious LLM through fine-tuning on an adversarial task; (ii) next, we quantize the malicious model and calculate constraints that characterize all full-precision models that map to the same quantized model; (iii) finally, using projected gradient descent, we tune out the poisoned behavior from the full-precision model while ensuring that its weights satisfy the constraints computed in step (ii). This procedure results in an LLM that exhibits benign behavior in full precision but when quantized, it follows the adversarial behavior injected in step (i). We experimentally demonstrate the feasibility and severity of such an attack across three diverse scenarios: vulnerable code generation, content injection, and over-refusal attack. In practice, the adversary could host the resulting full-precision model on an LLM community hub such as Hugging Face, exposing millions of users to the threat of deploying its malicious quantized version on their devices.

Watermarking is a technical means to dissuade malfeasant usage of Large Language Models. This paper proposes a novel watermarking scheme, so-called WaterMax, that enjoys high detectability while sustaining the quality of the generated text of the original LLM. Its new design leaves the LLM untouched (no modification of the weights, logits or temperature). WaterMax balances robustness and computational complexity contrary to the watermarking techniques of the literature inherently provoking a trade-off between quality and robustness. Its performance is both theoretically proven and experimentally validated. It outperforms all the SotA techniques under the most complete benchmark suite.

Machine learning practitioners often face significant challenges in formally integrating their prior knowledge and beliefs into predictive models, limiting the potential for nuanced and context-aware analyses. Moreover, the expertise needed to integrate this prior knowledge into probabilistic modeling typically limits the application of these models to specialists. Our goal is to build a regression model that can process numerical data and make probabilistic predictions at arbitrary locations, guided by natural language text which describes a user's prior knowledge. Large Language Models (LLMs) provide a useful starting point for designing such a tool since they 1) provide an interface where users can incorporate expert insights in natural language and 2) provide an opportunity for leveraging latent problem-relevant knowledge encoded in LLMs that users may not have themselves. We start by exploring strategies for eliciting explicit, coherent numerical predictive distributions from LLMs. We examine these joint predictive distributions, which we call LLM Processes, over arbitrarily-many quantities in settings such as forecasting, multi-dimensional regression, black-box optimization, and image modeling. We investigate the practical details of prompting to elicit coherent predictive distributions, and demonstrate their effectiveness at regression. Finally, we demonstrate the ability to usefully incorporate text into numerical predictions, improving predictive performance and giving quantitative structure that reflects qualitative descriptions. This lets us begin to explore the rich, grounded hypothesis space that LLMs implicitly encode.

LLMs are computationally expensive to pre-train due to their large scale. Model growth emerges as a promising approach by leveraging smaller models to accelerate the training of larger ones. However, the viability of these model growth methods in efficient LLM pre-training remains underexplored. This work identifies three critical $\underline{\textit{O}}$bstacles: ($\textit{O}$1) lack of comprehensive evaluation, ($\textit{O}$2) untested viability for scaling, and ($\textit{O}$3) lack of empirical guidelines. To tackle $\textit{O}$1, we summarize existing approaches into four atomic growth operators and systematically evaluate them in a standardized LLM pre-training setting. Our findings reveal that a depthwise stacking operator, called $G_{\text{stack}}$, exhibits remarkable acceleration in training, leading to decreased loss and improved overall performance on eight standard NLP benchmarks compared to strong baselines. Motivated by these promising results, we conduct extensive experiments to delve deeper into $G_{\text{stack}}$ to address $\textit{O}$2 and $\textit{O}$3. For $\textit{O}$2 (untested scalability), our study shows that $G_{\text{stack}}$ is scalable and consistently performs well, with experiments up to 7B LLMs after growth and pre-training LLMs with 750B tokens. For example, compared to a conventionally trained 7B model using 300B tokens, our $G_{\text{stack}}$ model converges to the same loss with 194B tokens, resulting in a 54.6\% speedup. We further address $\textit{O}$3 (lack of empirical guidelines) by formalizing guidelines to determine growth timing and growth factor for $G_{\text{stack}}$, making it practical in general LLM pre-training. We also provide in-depth discussions and comprehensive ablation studies of $G_{\text{stack}}$. Our code and pre-trained model are available at https://llm-stacking.github.io/.

Personalization has emerged as a critical research area in modern intelligent systems, focusing on mining users' behavioral history and adapting to their preferences for delivering tailored experiences. Despite the remarkable few-shot capabilities exhibited by black-box large language models (LLMs), the inherent opacity of their model parameters presents significant challenges in aligning the generated output with individual expectations. Existing solutions have primarily focused on prompt design to incorporate user-specific profiles and behaviors; however, such approaches often struggle to generalize effectively due to their inability to capture shared knowledge among all users. To address these challenges, we propose HYDRA, a model factorization framework that captures both user-specific behavior patterns from historical data and shared general knowledge among all users to deliver personalized generation. In order to capture user-specific behavior patterns, we first train a reranker to prioritize the most useful information from top-retrieved relevant historical records. By combining the prioritized history with the corresponding query, we train an adapter to align the output with individual user-specific preferences, eliminating the reliance on access to inherent model parameters of black-box LLMs. Both the reranker and the adapter can be decomposed into a base model with multiple user-specific heads, resembling a hydra. The base model maintains shared knowledge across users, while the multiple personal heads capture user-specific preferences. Experimental results demonstrate that \method outperforms existing state-of-the-art prompt-based methods by an average relative improvement of 9.01% across five diverse personalization tasks in the LaMP benchmark.

Infrastructure-as-Code (IaC), an important component of cloud computing, allows the definition of cloud infrastructure in high-level programs. However, developing IaC programs is challenging, complicated by factors that include the burgeoning complexity of the cloud ecosystem (e.g., diversity of cloud services and workloads), and the relative scarcity of IaC-specific code examples and public repositories. While large language models (LLMs) have shown promise in general code generation and could potentially aid in IaC development, no benchmarks currently exist for evaluating their ability to generate IaC code. We present IaC-Eval, a first step in this research direction. IaC-Eval's dataset includes 458 human-curated scenarios covering a wide range of popular AWS services, at varying difficulty levels. Each scenario mainly comprises a natural language IaC problem description and an infrastructure intent specification. The former is fed as user input to the LLM, while the latter is a general notion used to verify if the generated IaC program conforms to the user's intent; by making explicit the problem's requirements that can encompass various cloud services, resources and internal infrastructure details. Our in-depth evaluation shows that contemporary LLMs perform poorly on IaC-Eval, with the top-performing model, GPT-4, obtaining a pass@1 accuracy of 19.36%. In contrast, it scores 86.6% on EvalPlus, a popular Python code generation benchmark, highlighting a need for advancements in this domain. We open-source the IaC-Eval dataset and evaluation framework at https://github.com/autoiac-project/iac-eval to enable future research on LLM-based IaC code generation.