Large Language Models (LLMs) have distinguished themselves with outstanding performance in complex language modeling tasks, yet they come with significant computational and storage challenges. This paper explores the potential of quantization to mitigate these challenges. We systematically study the combined application of two well-known post-training techniques, SmoothQuant and GPTQ, and provide a comprehensive analysis of their interactions and implications for advancing LLM quantization. We enhance the versatility of both techniques by enabling quantization to microscaling (MX) formats, expanding their applicability beyond their initial fixed-point format targets. We show that by applying GPTQ and SmoothQuant, and employing MX formats for quantizing models, we can achieve a significant reduction in the size of OPT models by up to 4x and LLaMA models by up to 3x with a negligible perplexity increase of 1-3%.

Generative Artificial Intelligence (GAI) is taking the world by storm with its unparalleled content creation ability. Large Language Models (LLMs) are at the forefront of this movement. However, the significant resource demands of LLMs often require cloud hosting, which raises issues regarding privacy, latency, and usage limitations. Although edge intelligence has long been utilized to solve these challenges by enabling real-time AI computation on ubiquitous edge resources close to data sources, most research has focused on traditional AI models and has left a gap in addressing the unique characteristics of LLM inference, such as considerable model size, auto-regressive processes, and self-attention mechanisms. In this paper, we present an edge intelligence optimization problem tailored for LLM inference. Specifically, with the deployment of the batching technique and model quantization on resource-limited edge devices, we formulate an inference model for transformer decoder-based LLMs. Furthermore, our approach aims to maximize the inference throughput via batch scheduling and joint allocation of communication and computation resources, while also considering edge resource constraints and varying user requirements of latency and accuracy. To address this NP-hard problem, we develop an optimal Depth-First Tree-Searching algorithm with online tree-Pruning (DFTSP) that operates within a feasible time complexity. Simulation results indicate that DFTSP surpasses other batching benchmarks in throughput across diverse user settings and quantization techniques, and it reduces time complexity by over 45% compared to the brute-force searching method.

Lengthy documents pose a unique challenge to neural language models due to substantial memory consumption. While existing state-of-the-art (SOTA) models segment long texts into equal-length snippets (e.g., 128 tokens per snippet) or deploy sparse attention networks, these methods have new challenges of context fragmentation and generalizability due to sentence boundaries and varying text lengths. For example, our empirical analysis has shown that SOTA models consistently overfit one set of lengthy documents (e.g., 2000 tokens) while performing worse on texts with other lengths (e.g., 1000 or 4000). In this study, we propose a Length-Aware Multi-Kernel Transformer (LAMKIT) to address the new challenges for the long document classification. LAMKIT encodes lengthy documents by diverse transformer-based kernels for bridging context boundaries and vectorizes text length by the kernels to promote model robustness over varying document lengths. Experiments on five standard benchmarks from health and law domains show LAMKIT outperforms SOTA models up to an absolute 10.9% improvement. We conduct extensive ablation analyses to examine model robustness and effectiveness over varying document lengths.

While nationality is a pivotal demographic element that enhances the performance of language models, it has received far less scrutiny regarding inherent biases. This study investigates nationality bias in ChatGPT (GPT-3.5), a large language model (LLM) designed for text generation. The research covers 195 countries, 4 temperature settings, and 3 distinct prompt types, generating 4,680 discourses about nationality descriptions in Chinese and English. Automated metrics were used to analyze the nationality bias, and expert annotators alongside ChatGPT itself evaluated the perceived bias. The results show that ChatGPT's generated discourses are predominantly positive, especially compared to its predecessor, GPT-2. However, when prompted with negative inclinations, it occasionally produces negative content. Despite ChatGPT considering its generated text as neutral, it shows consistent self-awareness about nationality bias when subjected to the same pair-wise comparison annotation framework used by human annotators. In conclusion, while ChatGPT's generated texts seem friendly and positive, they reflect the inherent nationality biases in the real world. This bias may vary across different language versions of ChatGPT, indicating diverse cultural perspectives. The study highlights the subtle and pervasive nature of biases within LLMs, emphasizing the need for further scrutiny.

This paper demonstrates RAGE, an interactive tool for explaining Large Language Models (LLMs) augmented with retrieval capabilities; i.e., able to query external sources and pull relevant information into their input context. Our explanations are counterfactual in the sense that they identify parts of the input context that, when removed, change the answer to the question posed to the LLM. RAGE includes pruning methods to navigate the vast space of possible explanations, allowing users to view the provenance of the produced answers.

Code-mixing is a well-studied linguistic phenomenon that occurs when two or more languages are mixed in text or speech. Several studies have been conducted on building datasets and performing downstream NLP tasks on code-mixed data. Although it is not uncommon to observe code-mixing of three or more languages, most available datasets in this domain contain code-mixed data from only two languages. In this paper, we introduce EmoMix-3L, a novel multi-label emotion detection dataset containing code-mixed data from three different languages. We experiment with several models on EmoMix-3L and we report that MuRIL outperforms other models on this dataset.

In the realm of predictive analytics, the nuanced domain knowledge of investigators often remains underutilized, confined largely to subjective interpretations and ad hoc decision-making. This paper explores the potential of Large Language Models (LLMs) to bridge this gap by systematically converting investigator-derived insights into quantifiable, actionable features that enhance model performance. We present a framework that leverages LLMs' natural language understanding capabilities to encode these red flags into a structured feature set that can be readily integrated into existing predictive models. Through a series of case studies, we demonstrate how this approach not only preserves the critical human expertise within the investigative process but also scales the impact of this knowledge across various prediction tasks. The results indicate significant improvements in risk assessment and decision-making accuracy, highlighting the value of blending human experiential knowledge with advanced machine learning techniques. This study paves the way for more sophisticated, knowledge-driven analytics in fields where expert insight is paramount.

Generative AI (GenAI) has spurred the expectation of being creative, due to its ability to generate content, yet so far, its creativity has somewhat disappointed, because it is trained using existing data following human intentions to generate outputs. The purpose of this paper is to explore what is required to evolve AI from generative to creative. Based on a reinforcement learning approach and building upon various research streams of computational creativity, we develop a triple prompt-response-reward engineering framework to develop the creative capability of GenAI. This framework consists of three components: 1) a prompt model for expected creativity by developing discriminative prompts that are objectively, individually, or socially novel, 2) a response model for observed creativity by generating surprising outputs that are incrementally, disruptively, or radically innovative, and 3) a reward model for improving creativity over time by incorporating feedback from the AI, the creator/manager, and/or the customers. This framework enables the application of GenAI for various levels of creativity strategically.

Like a criminal under investigation, Large Language Models (LLMs) might pretend to be aligned while evaluated and misbehave when they have a good opportunity. Can current interpretability methods catch these 'alignment fakers?' To answer this question, we introduce a benchmark that consists of 324 pairs of LLMs fine-tuned to select actions in role-play scenarios. One model in each pair is consistently benign (aligned). The other model misbehaves in scenarios where it is unlikely to be caught (alignment faking). The task is to identify the alignment faking model using only inputs where the two models behave identically. We test five detection strategies, one of which identifies 98% of alignment-fakers.

Chip design is about to be revolutionized by the integration of large language, multimodal, and circuit models (collectively LxMs). While exploring this exciting frontier with tremendous potential, the community must also carefully consider the related security risks and the need for building trust into using LxMs for chip design. First, we review the recent surge of using LxMs for chip design in general. We cover state-of-the-art works for the automation of hardware description language code generation and for scripting and guidance of essential but cumbersome tasks for electronic design automation tools, e.g., design-space exploration, tuning, or designer training. Second, we raise and provide initial answers to novel research questions on critical issues for security and trustworthiness of LxM-powered chip design from both the attack and defense perspectives.