Logic reasoning has been critically needed in problem-solving and decision-making. Although Language Models (LMs) have demonstrated capabilities of handling multiple reasoning tasks (e.g., commonsense reasoning), their ability to reason complex mathematical problems, specifically propositional logic, remains largely underexplored. This lack of exploration can be attributed to the limited availability of annotated corpora. Here, we present a well-labeled propositional logic corpus, LogicPrpBank, containing 7093 Propositional Logic Statements (PLSs) across six mathematical subjects, to study a brand-new task of reasoning logical implication and equivalence. We benchmark LogicPrpBank with widely-used LMs to show that our corpus offers a useful resource for this challenging task and there is ample room for model improvement.

As Large Language Models (LLMs) gain wider adoption in various contexts, it becomes crucial to ensure they are reasonably safe, consistent, and reliable for an application at hand. This may require probing or auditing them. Probing LLMs with varied iterations of a single question could reveal potential inconsistencies in their knowledge or functionality. However, a tool for performing such audits with simple workflow and low technical threshold is lacking. In this demo, we introduce "AuditLLM," a novel tool designed to evaluate the performance of various LLMs in a methodical way. AuditLLM's core functionality lies in its ability to test a given LLM by auditing it using multiple probes generated from a single question, thereby identifying any inconsistencies in the model's understanding or operation. A reasonably robust, reliable, and consistent LLM should output semantically similar responses for a question asked differently or by different people. Based on this assumption, AuditLLM produces easily interpretable results regarding the LLM's consistencies from a single question that the user enters. A certain level of inconsistency has been shown to be an indicator of potential bias, hallucinations, and other issues. One could then use the output of AuditLLM to further investigate issues with the aforementioned LLM. To facilitate demonstration and practical uses, AuditLLM offers two key modes: (1) Live mode which allows instant auditing of LLMs by analyzing responses to real-time queries; (2) Batch mode which facilitates comprehensive LLM auditing by processing multiple queries at once for in-depth analysis. This tool is beneficial for both researchers and general users, as it enhances our understanding of LLMs' capabilities in generating responses, using a standardized auditing platform.

Large Language Models (LLMs) have surged in popularity in recent months, but they have demonstrated concerning capabilities to generate harmful content when manipulated. While techniques like safety fine-tuning aim to minimize harmful use, recent works have shown that LLMs remain vulnerable to attacks that elicit toxic responses. In this work, we introduce the Proxy-Guided Attack on LLMs (PAL), the first optimization-based attack on LLMs in a black-box query-only setting. In particular, it relies on a surrogate model to guide the optimization and a sophisticated loss designed for real-world LLM APIs. Our attack achieves 84% attack success rate (ASR) on GPT-3.5-Turbo and 48% on Llama-2-7B, compared to 4% for the current state of the art. We also propose GCG++, an improvement to the GCG attack that reaches 94% ASR on white-box Llama-2-7B, and the Random-Search Attack on LLMs (RAL), a strong but simple baseline for query-based attacks. We believe the techniques proposed in this work will enable more comprehensive safety testing of LLMs and, in the long term, the development of better security guardrails. The code can be found at https://github.com/chawins/pal.

This investigation reveals a novel exploit derived from PNG image file formats, specifically their alpha transparency layer, and its potential to fool multiple AI vision systems. Our method uses this alpha layer as a clandestine channel invisible to human observers but fully actionable by AI image processors. The scope tested for the vulnerability spans representative vision systems from Apple, Microsoft, Google, Salesforce, Nvidia, and Facebook, highlighting the attack's potential breadth. This vulnerability challenges the security protocols of existing and fielded vision systems, from medical imaging to autonomous driving technologies. Our experiments demonstrate that the affected systems, which rely on convolutional neural networks or the latest multimodal language models, cannot quickly mitigate these vulnerabilities through simple patches or updates. Instead, they require retraining and architectural changes, indicating a persistent hole in multimodal technologies without some future adversarial hardening against such vision-language exploits.

The training of large language models (LLMs) is expensive. In this paper, we study data-efficient approaches for pre-training LLMs, i.e., techniques that aim to optimize the Pareto frontier of model quality and training resource/data consumption. We seek to understand the tradeoffs associated with data selection routines based on (i) expensive-to-compute data-quality estimates, and (ii) maximization of coverage and diversity-based measures in the feature space. Our first technique, Ask-LLM, leverages the zero-shot reasoning capabilities of instruction-tuned LLMs to directly assess the quality of a training example. To target coverage, we propose Density sampling, which models the data distribution to select a diverse sample. In our comparison of 19 samplers, involving hundreds of evaluation tasks and pre-training runs, we find that Ask-LLM and Density are the best methods in their respective categories. Coverage sampling can recover the performance of the full data, while models trained on Ask-LLM data consistently outperform full-data training -- even when we reject 90% of the original dataset, while converging up to 70% faster.

This study investigates GPT-4's assessment of its performance in healthcare applications. A simple prompting technique was used to prompt the LLM with questions taken from the United States Medical Licensing Examination (USMLE) questionnaire and it was tasked to evaluate its confidence score before posing the question and after asking the question. The questionnaire was categorized into two groups-questions with feedback (WF) and questions with no feedback(NF) post-question. The model was asked to provide absolute and relative confidence scores before and after each question. The experimental findings were analyzed using statistical tools to study the variability of confidence in WF and NF groups. Additionally, a sequential analysis was conducted to observe the performance variation for the WF and NF groups. Results indicate that feedback influences relative confidence but doesn't consistently increase or decrease it. Understanding the performance of LLM is paramount in exploring its utility in sensitive areas like healthcare. This study contributes to the ongoing discourse on the reliability of AI, particularly of LLMs like GPT-4, within healthcare, offering insights into how feedback mechanisms might be optimized to enhance AI-assisted medical education and decision support.

Protein research is crucial in various fundamental disciplines, but understanding their intricate structure-function relationships remains challenging. Recent Large Language Models (LLMs) have made significant strides in comprehending task-specific knowledge, suggesting the potential for ChatGPT-like systems specialized in protein to facilitate basic research. In this work, we introduce ProtChatGPT, which aims at learning and understanding protein structures via natural languages. ProtChatGPT enables users to upload proteins, ask questions, and engage in interactive conversations to produce comprehensive answers. The system comprises protein encoders, a Protein-Language Pertaining Transformer (PLP-former), a projection adapter, and an LLM. The protein first undergoes protein encoders and PLP-former to produce protein embeddings, which are then projected by the adapter to conform with the LLM. The LLM finally combines user questions with projected embeddings to generate informative answers. Experiments show that ProtChatGPT can produce promising responses to proteins and their corresponding questions. We hope that ProtChatGPT could form the basis for further exploration and application in protein research. Code and our pre-trained model will be publicly available.

This work aims to build a text embedder that can capture characteristics of texts specified by user instructions. Despite its tremendous potential to deploy user-oriented embeddings, none of previous approaches provides a concrete solution for it. This paper offers a new viewpoint, which treats the instruction as a question about the input text and encodes the expected answers to obtain the representation accordingly. Intuitively, texts with the same (implicit) semantics would share similar answers following the instruction, thus leading to more similar embeddings. Specifically, we propose InBedder that instantiates this embed-via-answering idea by only fine-tuning language models on abstractive question answering tasks. InBedder demonstrates significantly improved instruction-following capabilities according to our proposed instruction awareness tests and instruction robustness tests, when applied to both large language models (LLMs) (e.g., llama-2-7b) and smaller encoder-based LMs (e.g., roberta-large). Additionally, our qualitative analysis of clustering outcomes, achieved by applying different instructions to the same corpus, demonstrates a high degree of interpretability.

The extraordinary performance of large language models has not only reshaped the research landscape in the field of NLP but has also demonstrated its exceptional applicative potential in various domains. However, the potential of these models in mining relationships from graph data remains under-explored. Graph neural networks, as a popular research area in recent years, have numerous studies on relationship mining. Yet, current cutting-edge research in graph neural networks has not been effectively integrated with large language models, leading to limited efficiency and capability in graph relationship mining tasks. A primary challenge is the inability of LLMs to deeply exploit the edge information in graphs, which is critical for understanding complex node relationships. This gap limits the potential of LLMs to extract meaningful insights from graph structures, limiting their applicability in more complex graph-based analysis. We focus on how to utilize existing LLMs for mining and understanding relationships in graph data, applying these techniques to recommendation tasks. We propose an innovative framework that combines the strong contextual representation capabilities of LLMs with the relationship extraction and analysis functions of GNNs for mining relationships in graph data. Specifically, we design a new prompt construction framework that integrates relational information of graph data into natural language expressions, aiding LLMs in more intuitively grasping the connectivity information within graph data. Additionally, we introduce graph relationship understanding and analysis functions into LLMs to enhance their focus on connectivity information in graph data. Our evaluation on real-world datasets demonstrates the framework's ability to understand connectivity information in graph data.

This paper considers the challenges that Large Language Models (LLMs) face when reasoning over text that includes information involving uncertainty explicitly quantified via probability values. This type of reasoning is relevant to a variety of contexts ranging from everyday conversations to medical decision-making. Despite improvements in the mathematical reasoning capabilities of LLMs, they still exhibit significant difficulties when it comes to probabilistic reasoning. To deal with this problem, we first introduce the Bayesian Linguistic Inference Dataset (BLInD), a new dataset specifically designed to test the probabilistic reasoning capabilities of LLMs. We then leverage this new dataset to thoroughly illustrate the specific limitations of LLMs for tasks involving probabilistic reasoning and present several strategies that map the problem to different formal representations, including Python code, probabilistic inference algorithms, and probabilistic logical programming. We Figure 1: An example from the BLInD dataset including conclude by providing an evaluation of our methods an underlying Bayesian network, its textual description, and on BLInD and on an adaptation of a causal reasoning probabilistic queries in natural language.