Freely Long-Thinking Transformer (FraiLT) is an improved transformer model designed to enhance processing capabilities without scaling up size. It utilizes a recursive approach, iterating over a subset of layers multiple times, and introduces iteration encodings to maintain awareness across these cycles. Iteration encoding allows FraiLT to achieve the interpretive depth of larger models in a compact form. When evaluated on a synthetic story dataset, FraiLT outperformed larger models, showcasing its ability to deliver high-quality performance while reducing memory demands. This model represents a step forward towards more efficient and accessible language models.

It has long been recognized that it is not enough for a Recommender System (RS) to provide recommendations based only on their relevance to users. Among many other criteria, the set of recommendations may need to be diverse in order to handle uncertainty and offer a meaningful choice. The literature reports many ways of measuring diversity and ways of improving the diversity of a set of recommendations, most notably by re-ranking and selecting from a larger set of candidate recommendations. Driven by promising insights from the literature on how to incorporate versatile Large Language Models (LLMs) into the RS pipeline, in this paper, we show how LLMs can be used for diversity re-ranking. We begin with an informal study that verifies that LLMs can be used for re-ranking tasks and do have some understanding of the concept of diversity. Then, we design a more rigorous methodology where LLMs are prompted to generate a diverse ranking from a candidate ranking using various prompt templates with different re-ranking instructions in a zero-shot fashion. We conduct comprehensive experiments testing state-of-the-art conversational LLMs from the GPT and Llama families. We compare their re-ranking capabilities with random re-ranking and various traditional re-ranking methods from the literature (MMR, xQuAD and RxQuAD). We find that LLM-based re-ranking outperforms random re-ranking across all the metrics that we use but does not perform as well as the traditional re-ranking methods. We gain insight into prompt design for this task (e.g.\ on the whole, it is better to prompt for diversity rather than a balance of diversity and relevance). Given that no special knowledge engineering is needed, we conclude that LLM-based re-ranking is a promising approach, and we highlight directions for future research. We open-source the code of our experiments for reproducibility.

Free-text radiology reports present a rich data source for various medical tasks, but effectively labeling these texts remains challenging. Traditional rule-based labeling methods fall short of capturing the nuances of diverse free-text patterns. Moreover, models using expert-annotated data are limited by data scarcity and pre-defined classes, impacting their performance, flexibility and scalability. To address these issues, our study offers three main contributions: 1) We demonstrate the potential of GPT as an adept labeler using carefully designed prompts. 2) Utilizing only the data labeled by GPT, we trained a BERT-based labeler, CheX-GPT, which operates faster and more efficiently than its GPT counterpart. 3) To benchmark labeler performance, we introduced a publicly available expert-annotated test set, MIMIC-500, comprising 500 cases from the MIMIC validation set. Our findings demonstrate that CheX-GPT not only excels in labeling accuracy over existing models, but also showcases superior efficiency, flexibility, and scalability, supported by our introduction of the MIMIC-500 dataset for robust benchmarking. Code and models are available at https://github.com/kakaobrain/CheXGPT.

Long text generation, such as novel writing or discourse-level translation with extremely long contexts, presents significant challenges to current language models. Existing methods mainly focus on extending the model's context window through strategies like length extrapolation. However, these approaches demand substantial hardware resources during the training and/or inference phases. Our proposed method, Temp-Lora, introduces an alternative concept. Instead of relying on the KV cache to store all context information, Temp-Lora embeds this information directly into the model's parameters. In the process of long text generation, we use a temporary Lora module, progressively trained with text generated previously. This approach not only efficiently preserves contextual knowledge but also prevents any permanent alteration to the model's parameters given that the module is discarded post-generation. Extensive experiments on the PG19 language modeling benchmark and the GuoFeng discourse-level translation benchmark validate the effectiveness of Temp-Lora. Our results show that: 1) Temp-Lora substantially enhances generation quality for long texts, as indicated by a 13.2% decrease in perplexity on a subset of PG19, and a 29.6% decrease in perplexity along with a 53.2% increase in BLEU score on GuoFeng, 2) Temp-Lora is compatible with and enhances most existing long text generation methods, and 3) Temp-Lora can greatly reduce computational costs by shortening the context window. While ensuring a slight improvement in generation quality (a decrease of 3.8% in PPL), it enables a reduction of 70.5% in the FLOPs required for inference and a 51.5% decrease in latency.

This paper presents an innovative approach to integrating Large Language Models (LLMs) with Arduino-controlled Electrohydrodynamic (EHD) pumps for precise color synthesis in automation systems. We propose a novel framework that employs fine-tuned LLMs to interpret natural language commands and convert them into specific operational instructions for EHD pump control. This approach aims to enhance user interaction with complex hardware systems, making it more intuitive and efficient. The methodology involves four key steps: fine-tuning the language model with a dataset of color specifications and corresponding Arduino code, developing a natural language processing interface, translating user inputs into executable Arduino code, and controlling EHD pumps for accurate color mixing. Conceptual experiment results, based on theoretical assumptions, indicate a high potential for accurate color synthesis, efficient language model interpretation, and reliable EHD pump operation. This research extends the application of LLMs beyond text-based tasks, demonstrating their potential in industrial automation and control systems. While highlighting the limitations and the need for real-world testing, this study opens new avenues for AI applications in physical system control and sets a foundation for future advancements in AI-driven automation technologies.

Large language models (LLMs) can solve problems step-by-step. While this chain-of-thought (CoT) reasoning boosts LLMs' performance, it is unclear if LLMs \textit{know} when to use CoT and whether those CoT are always necessary to answer the question. This paper shows that LLMs tend to generate redundant calculations and reasoning on a manually constructed math QA dataset, GSM8K-Zero. GSM8K-Zero is constructed such that the questions can be answered without any calculations, but LLMs, including Llama-2 models and Claude-2, tend to generate lengthy and unnecessary calculations to answer the questions. We also conduct experiments to explain why LLMs generate redundant calculations and reasonings. GSM8K-Zero is publicly available at https://github.com/d223302/Over-Reasoning-of-LLMs and https://huggingface.co/datasets/dcml0714/GSM8K-Zero.

Large language models (LLMs) with Transformer architectures have become phenomenal in natural language processing, multimodal generative artificial intelligence, and agent-oriented artificial intelligence. The self-attention module is the most dominating sub-structure inside Transformer-based LLMs. Computation using general-purpose graphics processing units (GPUs) inflicts reckless demand for I/O bandwidth for transferring intermediate calculation results between memories and processing units. To tackle this challenge, this work develops a fully customized vanilla self-attention accelerator, AttentionLego, as the basic building block for constructing spatially expandable LLM processors. AttentionLego provides basic implementation with fully-customized digital logic incorporating Processing-In-Memory (PIM) technology. It is based on PIM-based matrix-vector multiplication and look-up table-based Softmax design. The open-source code is available online: https://bonany.cc/attentionleg.

The success of AI assistants based on Language Models (LLMs) hinges on Reinforcement Learning from Human Feedback (RLHF) to comprehend and align with user intentions. However, traditional alignment algorithms, such as PPO, are hampered by complex annotation and training requirements. This reliance limits the applicability of RLHF and hinders the development of professional assistants tailored to diverse human preferences. In this work, we introduce \textit{Linear Alignment}, a novel algorithm that aligns language models with human preferences in one single inference step, eliminating the reliance on data annotation and model training. Linear alignment incorporates a new parameterization for policy optimization under divergence constraints, which enables the extraction of optimal policy in a closed-form manner and facilitates the direct estimation of the aligned response. Extensive experiments on both general and personalized preference datasets demonstrate that linear alignment significantly enhances the performance and efficiency of LLM alignment across diverse scenarios. Our code and dataset will be published on \url{https://github.com/Wizardcoast/Linear_Alignment.git}.

Generative AI models face the challenge of hallucinations that can undermine users' trust in such systems. We approach the problem of conversational information seeking as a two-step process, where relevant passages in a corpus are identified first and then summarized into a final system response. This way we can automatically assess if the answer to the user's question is present in the corpus. Specifically, our proposed method employs a sentence-level classifier to detect if the answer is present, then aggregates these predictions on the passage level, and eventually across the top-ranked passages to arrive at a final answerability estimate. For training and evaluation, we develop a dataset based on the TREC CAsT benchmark that includes answerability labels on the sentence, passage, and ranking levels. We demonstrate that our proposed method represents a strong baseline and outperforms a state-of-the-art LLM on the answerability prediction task.

Figure 1: We propose General Flow as Foundation Affordance. Its properties and applications are analyzed to reveal its great power. We design a scale-aware algorithm for general flow prediction and achieve stable zero-shot cross-embodiment skill transfer in the real world. Abstract--We address the challenge of acquiring real-world guidance, thus facilitating stable zero-shot skill transfer in realworld manipulation skills with a scalable framework. We deploy our method with a policy based on the success of large-scale auto-regressive prediction in Large closed-loop flow prediction. Remarkably, without any additional Language Models (LLMs), we hold the belief that identifying training, our method achieves an impressive 81% success rate an appropriate prediction target capable of leveraging largescale in human-to-robot skill transfer, covering 18 tasks in 6 scenes. Therefore, we propose to utilize flow, which represents leveraging cross-embodiment data resources; (2) universality: the future trajectories of 3D points on objects of interest, as an multiple object categories, including rigid, articulated, and soft ideal prediction target in robot learning. To exploit scalable data bodies; (3) stable skill transfer: providing actionable guidance resources, we turn our attention to cross-embodiment datasets. These lead to a new pathway We develop, for the first time, a language-conditioned prediction towards scalable general robot learning. We first develop pipelines to extract 3D flow labels We aim to reveal a potential pathway for replicating the directly from RGBD human video datasets. We find prediction success of Large Language Models (LLMs) in the domain of of dense flow in real-world scene point clouds remains robot learning. Specifically, we are interested in developing a formidable challenge, primarily due to the variability of a new framework that enables scalable learning for robot trajectory scales and the need to enhance robustness in zeroshot manipulation. To address these issues, we employ scale-aware the future, this framework has the potential to progressively strategies in both the data and model aspects, complemented enhance the capabilities of robots, i.e., the scaling law that has by augmentation techniques that focus on embodiment occlusion been observed in LLMs [82]. Inspired by the LLMs training (human hand and robot arm) and query point sampling paradigm [14], we believe that two key elements contribute to (3D points on objects of interest), thereby boosting zero-shot their strong generalization abilities: (1) a vast training dataset stability.