Unfortunately, the post-processing methods widely used in existing studies are suboptimal for In recent years, Large Language Models (LLMs) the applications of hallucination detection models have demonstrated remarkable performance in a variety for LLMs in practice. First, existing postprocessing of natural language processing (NLP) applications methods often suffer from extreme computation (Brown et al., 2020; Chowdhery et al., 2022; costs and high latency. In order to identify Touvron et al., 2023a; Scao et al., 2022; Zhang hallucinations in input text without ground et al., 2022). However, the widespread adoption of truth references (otherwise the task would downgrade LLMs has highlighted a critical problem, i.e., hallucination. to a simple fact verification task), hallucination Hallucination refers to the cases where detection models need to be powerful and LLMs generate responses that are logically coherent knowledgeable on their own. SOTA detection methods but factually incorrect or misleading (Maynez are often implemented with LLMs (e.g., chat-et al., 2020; Zhou et al., 2020; Liu et al., 2021; GPT, LLaMA, OPT) directly (Manakul et al., 2023;

The success of Large Language Models (LLMs) has led to a parallel rise in the development of Large Multimodal Models (LMMs), which have begun to transform a variety of applications. These sophisticated multimodal models are designed to interpret and analyze complex data by integrating multiple modalities such as text and images, thereby opening new avenues for a range of applications. This paper investigates the applicability and effectiveness of prompt-engineered LMMs that process both images and text, including models such as LLaVA, BakLLaVA, Moondream, Gemini-pro-vision, and GPT-4o, compared to fine-tuned Vision Transformer (ViT) models in addressing critical security challenges. We focus on two distinct security tasks: 1) a visually evident task of detecting simple triggers, such as small pixel variations in images that could be exploited to access potential backdoors in the models, and 2) a visually non-evident task of malware classification through visual representations. In the visually evident task, some LMMs, such as Gemini-pro-vision and GPT-4o, have demonstrated the potential to achieve good performance with careful prompt engineering, with GPT-4o achieving the highest accuracy and F1-score of 91.9\% and 91\%, respectively. However, the fine-tuned ViT models exhibit perfect performance in this task due to its simplicity. For the visually non-evident task, the results highlight a significant divergence in performance, with ViT models achieving F1-scores of 97.11\% in predicting 25 malware classes and 97.61\% in predicting 5 malware families, whereas LMMs showed suboptimal performance despite iterative prompt improvements. This study not only showcases the strengths and limitations of prompt-engineered LMMs in cybersecurity applications but also emphasizes the unmatched efficacy of fine-tuned ViT models for precise and dependable tasks.

In recent years, large language models (LLMs) have demonstrated notable success across various tasks, but the trustworthiness of LLMs is still an open problem. One specific threat is the potential to generate toxic or harmful responses. Attackers can craft adversarial prompts that induce harmful responses from LLMs. In this work, we pioneer a theoretical foundation in LLMs security by identifying bias vulnerabilities within the safety fine-tuning and design a black-box jailbreak method named DRA (Disguise and Reconstruction Attack), which conceals harmful instructions through disguise and prompts the model to reconstruct the original harmful instruction within its completion. We evaluate DRA across various open-source and closed-source models, showcasing state-of-the-art jailbreak success rates and attack efficiency. Notably, DRA boasts a 91.1% attack success rate on OpenAI GPT-4 chatbot.

Reconstructing natural language from non-invasive electroencephalography (EEG) holds great promise as a language decoding technology for brain-computer interfaces (BCIs). However, EEG-based language decoding is still in its nascent stages, facing several technical issues such as: 1) Absence of a hybrid strategy that can effectively integrate cross-modality (between EEG and text) self-learning with intra-modality self-reconstruction of EEG features or textual sequences; 2) Under-utilization of large language models (LLMs) to enhance EEG-based language decoding. To address above issues, we propose the Contrastive EEG-Text Masked Autoencoder (CET-MAE), a novel model that orchestrates compound self-supervised learning across and within EEG and text through a dedicated multi-stream encoder. Furthermore, we develop a framework called E2T-PTR (EEG-to-Text decoding using Pretrained Transferable Representations), which leverages pre-trained modules alongside the EEG stream from CET-MAE and further enables an LLM (specifically BART) to decode text from EEG sequences. Comprehensive experiments conducted on the popular text-evoked EEG database, ZuCo, demonstrate the superiority of E2T-PTR, which outperforms the state-of-the-art in ROUGE-1 F1 and BLEU-4 scores by 8.34% and 32.21%, respectively. These results indicate significant advancements in the field and underscores the proposed framework's potential to enable more powerful and widespread BCI applications.

This paper addresses the challenge of train-short-test-long (TSTL) scenarios in Large Language Models (LLMs) equipped with Rotary Position Embedding (RoPE), where models pre-trained on shorter sequences face difficulty with out-of-distribution (OOD) token positions in longer sequences. We introduce Resonance RoPE, a novel approach designed to narrow the generalization gap in TSTL scenarios by refining the interpolation of RoPE features for OOD positions, significantly improving the model performance without additional online computational costs. Furthermore, we present PosGen, a new synthetic benchmark specifically designed for fine-grained behavior analysis in TSTL scenarios, aiming to isolate the constantly increasing difficulty of token generation on long contexts from the challenges of recognizing new token positions. Our experiments on synthetic tasks show that after applying Resonance RoPE, Transformers recognize OOD position better and more robustly. Our extensive LLM experiments also show superior performance after applying Resonance RoPE to the current state-of-the-art RoPE scaling method, YaRN, on both upstream language modeling tasks and a variety of downstream long-text applications.

Can Transformers predict new syllogisms by composing established ones? More generally, what type of targets can be learned by such models from scratch? Recent works show that Transformers can be Turing-complete in terms of expressivity, but this does not address the learnability objective. This paper puts forward the notion of 'distribution locality' to capture when weak learning is efficiently achievable by regular Transformers, where the locality measures the least number of tokens required in addition to the tokens histogram to correlate nontrivially with the target. As shown experimentally and theoretically under additional assumptions, distributions with high locality cannot be learned efficiently. In particular, syllogisms cannot be composed on long chains. Furthermore, we show that (i) an agnostic scratchpad cannot help to break the locality barrier, (ii) an educated scratchpad can help if it breaks the locality at each step, (iii) a notion of 'inductive scratchpad' can both break the locality and improve the out-of-distribution generalization, e.g., generalizing to almost double input size for some arithmetic tasks.

Stochastic dominance is an important concept in probability theory, econometrics and social choice theory for robustly modeling agents' preferences between random outcomes. While many works have been dedicated to the univariate case, little has been done in the multivariate scenario, wherein an agent has to decide between different multivariate outcomes. By exploiting a characterization of multivariate first stochastic dominance in terms of couplings, we introduce a statistic that assesses multivariate almost stochastic dominance under the framework of Optimal Transport with a smooth cost. Further, we introduce an entropic regularization of this statistic, and establish a central limit theorem (CLT) and consistency of the bootstrap procedure for the empirical statistic. Armed with this CLT, we propose a hypothesis testing framework as well as an efficient implementation using the Sinkhorn algorithm. We showcase our method in comparing and benchmarking Large Language Models that are evaluated on multiple metrics. Our multivariate stochastic dominance test allows us to capture the dependencies between the metrics in order to make an informed and statistically significant decision on the relative performance of the models.

The original version of this story appeared in Quanta Magazine. Imagine you had a friend who gave different answers to the same question, depending on how you asked it. "What's the capital of Peru?" would get one answer, and "Is Lima the capital of Peru?" would get another. You'd probably be a little worried about your friend's mental faculties, and you'd almost certainly find it hard to trust any answer they gave. A generative question, which is open-ended, yields one answer, and a discriminative question, which involves having to choose between options, often yields a different one.

Visual Question Answering (VQA) is an important task in multimodal AI, and it is often used to test the ability of vision-language models to understand and reason on knowledge present in both visual and textual data. However, most of the current VQA models use datasets that are primarily focused on English and a few major world languages, with images that are typically Western-centric. While recent efforts have tried to increase the number of languages covered on VQA datasets, they still lack diversity in low-resource languages. More importantly, although these datasets often extend their linguistic range via translation or some other approaches, they usually keep images the same, resulting in narrow cultural representation. To address these limitations, we construct CVQA, a new Culturally-diverse multilingual Visual Question Answering benchmark, designed to cover a rich set of languages and cultures, where we engage native speakers and cultural experts in the data collection process. As a result, CVQA includes culturally-driven images and questions from across 28 countries on four continents, covering 26 languages with 11 scripts, providing a total of 9k questions. We then benchmark several Multimodal Large Language Models (MLLMs) on CVQA, and show that the dataset is challenging for the current state-of-the-art models. This benchmark can serve as a probing evaluation suite for assessing the cultural capability and bias of multimodal models and hopefully encourage more research efforts toward increasing cultural awareness and linguistic diversity in this field.

Psychiatric evaluation nowadays is heavily dependent on the patient's verbal report about disturbed feelings, thoughts, behaviors and their changes over time. Accordingly, evaluation hinges on two main components: unstructured interviews, which allow patients to express themselves freely under the guidance of open questions, and structured questionnaires, aimed at standardizing the assessment. These methods are outlined in the Diagnostic and Statistical Manual of Mental Disorders (DSM) series, which attempts to assign universal scores to individual experiences of mental disorders [1]. However, the inherent complexity of mental health conditions, characterized by a known positive manifold of symptoms and compounded by the subjective nature and potential unreliability of self-reported data (especially from one session to another), along with interviewer biases, make accurate diagnosis challenging. The overlapping symptoms and the instability of mental state, especially in pathological conditions, further complicate the need for precision, precluding an objective and quantitative account of a critical element in the psychiatric evaluation process; the subjective self-experience [2, 3, 4]. The evolution of psychiatric practice is increasingly shaped by the integration of Natural Language Processing (NLP) and machine learning within traditional diagnostic approaches.