The development of Large Language Models (LLMs) has notably transformed numerous sectors, offering impressive text generation capabilities. Yet, the reliability and truthfulness of these models remain pressing concerns. To this end, we investigate iterative prompting, a strategy hypothesized to refine LLM responses, assessing its impact on LLM truthfulness, an area which has not been thoroughly explored. Our extensive experiments delve into the intricacies of iterative prompting variants, examining their influence on the accuracy and calibration of model responses. Our findings reveal that naive prompting methods significantly undermine truthfulness, leading to exacerbated calibration errors. In response to these challenges, we introduce several prompting variants designed to address the identified issues. These variants demonstrate marked improvements over existing baselines, signaling a promising direction for future research. Our work provides a nuanced understanding of iterative prompting and introduces novel approaches to enhance the truthfulness of LLMs, thereby contributing to the development of more accurate and trustworthy AI systems.
Large Language Models (LLMs) have drawn a lot of attention due to their strong performance on a wide range of natural language tasks, since the release of ChatGPT in November 2022. LLMs' ability of general-purpose language understanding and generation is acquired by training billions of model's parameters on massive amounts of text data, as predicted by scaling laws \cite{kaplan2020scaling,hoffmann2022training}. The research area of LLMs, while very recent, is evolving rapidly in many different ways. In this paper, we review some of the most prominent LLMs, including three popular LLM families (GPT, LLaMA, PaLM), and discuss their characteristics, contributions and limitations. We also give an overview of techniques developed to build, and augment LLMs. We then survey popular datasets prepared for LLM training, fine-tuning, and evaluation, review widely used LLM evaluation metrics, and compare the performance of several popular LLMs on a set of representative benchmarks. Finally, we conclude the paper by discussing open challenges and future research directions.
Large Language Models' success on text generation has also made them better at code generation and coding tasks. While a lot of work has demonstrated their remarkable performance on tasks such as code completion and editing, it is still unclear as to why. We help bridge this gap by exploring to what degree auto-regressive models understand the logical constructs of the underlying programs. We propose Counterfactual Analysis for Programming Concept Predicates (CACP) as a counterfactual testing framework to evaluate whether Large Code Models understand programming concepts. With only black-box access to the model, we use CACP to evaluate ten popular Large Code Models for four different programming concepts. Our findings suggest that current models lack understanding of concepts such as data flow and control flow.
Large Language Models (LLMs) have exhibited remarkable success in long-form context comprehension tasks. However, their capacity to generate long contents, such as reports and articles, remains insufficiently explored. Current benchmarks do not adequately assess LLMs' ability to produce informative and comprehensive content, necessitating a more rigorous evaluation approach. In this study, we introduce \textsc{ProxyQA}, a framework for evaluating long-form text generation, comprising in-depth human-curated \textit{meta-questions} spanning various domains. Each meta-question contains corresponding \textit{proxy-questions} with annotated answers. LLMs are prompted to generate extensive content in response to these meta-questions. Utilizing an evaluator and incorporating generated content as background context, \textsc{ProxyQA} evaluates the quality of generated content based on the evaluator's performance in answering the \textit{proxy-questions}. We examine multiple LLMs, emphasizing \textsc{ProxyQA}'s demanding nature as a high-quality assessment tool. Human evaluation demonstrates that evaluating through \textit{proxy-questions} is a highly self-consistent and human-criteria-correlated validation method. The dataset and leaderboard will be available at \url{https://github.com/Namco0816/ProxyQA}.
Language models serve as a cornerstone in natural language processing (NLP), utilizing mathematical methods to generalize language laws and knowledge for prediction and generation. Over extensive research spanning decades, language modeling has progressed from initial statistical language models (SLMs) to the contemporary landscape of large language models (LLMs). Notably, the swift evolution of LLMs has reached the ability to process, understand, and generate human-level text. Nevertheless, despite the significant advantages that LLMs offer in improving both work and personal lives, the limited understanding among general practitioners about the background and principles of these models hampers their full potential. Notably, most LLMs reviews focus on specific aspects and utilize specialized language, posing a challenge for practitioners lacking relevant background knowledge. In light of this, this survey aims to present a comprehensible overview of LLMs to assist a broader audience. It strives to facilitate a comprehensive understanding by exploring the historical background of language models and tracing their evolution over time. The survey further investigates the factors influencing the development of LLMs, emphasizing key contributions. Additionally, it concentrates on elucidating the underlying principles of LLMs, equipping audiences with essential theoretical knowledge. The survey also highlights the limitations of existing work and points out promising future directions.
We consider the task of generating structured representations of text using large language models (LLMs). We focus on tables and mind maps as representative modalities. Tables are more organized way of representing data, while mind maps provide a visually dynamic and flexible approach, particularly suitable for sparse content. Despite the effectiveness of LLMs on different tasks, we show that current models struggle with generating structured outputs. In response, we present effective prompting strategies for both of these tasks. We introduce a taxonomy of problems around factuality, global and local structure, common to both modalities and propose a set of critiques to tackle these issues resulting in an absolute improvement in accuracy of +37pp (79%) for mind maps and +15pp (78%) for tables. To evaluate semantic coverage of generated structured representations we propose Auto-QA, and we verify the adequacy of Auto-QA using SQuAD dataset. We further evaluate the usefulness of structured representations via a text comprehension user study. The results show a significant reduction in comprehension time compared to text when using table (42.9%) and mind map (31.9%), without loss in accuracy.
Watermark text spotting in document images can offer access to an often unexplored source of information, providing crucial evidence about a record's scope, audience and sometimes even authenticity. Stemming from the problem of text spotting, detecting and understanding watermarks in documents inherits the same hardships - in the wild, writing can come in various fonts, sizes and forms, making generic recognition a very difficult problem. To address the lack of resources in this field and propel further research, we propose a novel benchmark (K-Watermark) containing 65,447 data samples generated using Wrender, a watermark text patterns rendering procedure. A validity study using humans raters yields an authenticity score of 0.51 against pre-generated watermarked documents. To prove the usefulness of the dataset and rendering technique, we developed an end-to-end solution (Wextract) for detecting the bounding box instances of watermark text, while predicting the depicted text. To deal with this specific task, we introduce a variance minimization loss and a hierarchical self-attention mechanism. To the best of our knowledge, we are the first to propose an evaluation benchmark and a complete solution for retrieving watermarks from documents surpassing baselines by 5 AP points in detection and 4 points in character accuracy.
In light of recent advances in multimodal Large Language Models (LLMs), there is increasing attention to scaling them from image-text data to more informative real-world videos. Compared to static images, video poses unique challenges for effective large-scale pre-training due to the modeling of its spatiotemporal dynamics. In this paper, we address such limitations in video-language pre-training with an efficient video decomposition that represents each video as keyframes and temporal motions. These are then adapted to an LLM using well-designed tokenizers that discretize visual and temporal information as a few tokens, thus enabling unified generative pre-training of videos, images, and text. At inference, the generated tokens from the LLM are carefully recovered to the original continuous pixel space to create various video content. Our proposed framework is both capable of comprehending and generating image and video content, as demonstrated by its competitive performance across 13 multimodal benchmarks in image and video understanding and generation. Our code and models will be available at https://video-lavit.github.io.
Large language models (LLMs) are vulnerable to jailbreak attacks - resulting in harmful, unethical, or biased text generations. However, existing jailbreaking methods are computationally costly. In this paper, we propose the weak-to-strong jailbreaking attack, an efficient method to attack aligned LLMs to produce harmful text. Our key intuition is based on the observation that jailbroken and aligned models only differ in their initial decoding distributions. The weak-to-strong attack's key technical insight is using two smaller models (a safe and an unsafe one) to adversarially modify a significantly larger safe model's decoding probabilities. We evaluate the weak-to-strong attack on 5 diverse LLMs from 3 organizations. The results show our method can increase the misalignment rate to over 99% on two datasets with just one forward pass per example. Our study exposes an urgent safety issue that needs to be addressed when aligning LLMs. As an initial attempt, we propose a defense strategy to protect against such attacks, but creating more advanced defenses remains challenging. The code for replicating the method is available at https://github.com/XuandongZhao/weak-to-strong
While audio quality is a key performance metric for various audio processing tasks, including generative modeling, its objective measurement remains a challenge. Audio-Language Models (ALMs) are pre-trained on audio-text pairs that may contain information about audio quality, the presence of artifacts, or noise. Given an audio input and a text prompt related to quality, an ALM can be used to calculate a similarity score between the two. Here, we exploit this capability and introduce PAM, a no-reference metric for assessing audio quality for different audio processing tasks. Contrary to other "reference-free" metrics, PAM does not require computing embeddings on a reference dataset nor training a task-specific model on a costly set of human listening scores. We extensively evaluate the reliability of PAM against established metrics and human listening scores on four tasks: text-to-audio (TTA), text-to-music generation (TTM), text-to-speech (TTS), and deep noise suppression (DNS). We perform multiple ablation studies with controlled distortions, in-the-wild setups, and prompt choices. Our evaluation shows that PAM correlates well with existing metrics and human listening scores. These results demonstrate the potential of ALMs for computing a general-purpose audio quality metric.