In this paper we propose that a restricted version of logical inference can be implemented with self-attention networks. We are aiming at showing that LLMs (Large Language Models) constructed with transformer networks can make logical inferences. We would reveal the potential of LLMs by analyzing self-attention networks, which are main components of transformer networks. Our approach is not based on semantics of natural languages but operations of logical inference. %point of view. We show that hierarchical constructions of self-attention networks with feed forward networks (FFNs) can implement top-down derivations for a class of logical formulae. We also show bottom-up derivations are also implemented for the same class. We believe that our results show that LLMs implicitly have the power of logical inference.

Large language models revolutionize Text2SQL through supervised fine-tuning, yet a crucial limitation is overlooked: the complexity of databases leads to an increased context length, consequently resulting in higher GPU memory demands for model fine-tuning. To address this issue, we propose LR-SQL. LR-SQL comprises two supervised fine-tuning models: the schema\_link model and the SQL\_generation model, with the schema\_link model serving as the focal point for streamlining the overall process. During the fine-tuning of the schema\_link model, LR-SQL breaks down the complete database into flexible combinations of tables with adjustable quantities, enabling the model to learn the relationships within the entire database from these dispersed slices. Furthermore, to enhance the model's ability to perceive the relationships among various discrete slices during inference, LR-SQL trains the model's Chain-of-Thought capability for this task. Experimental results demonstrate that LR-SQL can reduce the total GPU memory usage by 40\% compared to existing fine-tuning methods, while only losing 2\% of table prediction accuracy in schema\_link task. For the overall Text2SQL task, the Execution Accuracy decrease by 0.6\%.Our project is now available on https://github.com/hongWin/LR-SQL

Quantization is a widely-used compression technology to reduce the overhead of serving large language models (LLMs) on terminal devices and in cloud data centers. However, prevalent quantization methods, such as 8-bit weight-activation or 4-bit weight-only quantization, achieve limited performance improvements due to poor support for low-precision (e.g., 4-bit) activation. This work, for the first time, realizes practical W4A4KV4 serving for LLMs, fully utilizing the INT4 tensor cores on modern GPUs and reducing the memory bottleneck caused by the KV cache. Specifically, we propose a novel fine-grained mixed-precision quantization algorithm (FMPQ) that compresses most activations into 4-bit with negligible accuracy loss. To support mixed-precision matrix multiplication for W4A4 and W4A8, we develop a highly optimized W4Ax kernel. Our approach introduces a novel mixed-precision data layout to facilitate access and fast dequantization for activation and weight tensors, utilizing the GPU's software pipeline to hide the overhead of data loading and conversion. Additionally, we propose fine-grained streaming multiprocessor (SM) scheduling to achieve load balance across different SMs. We integrate the optimized W4Ax kernel into our inference framework, COMET, and provide efficient management to support popular LLMs such as LLaMA-3-70B. Extensive evaluations demonstrate that, when running LLaMA family models on a single A100-80G-SMX4, COMET achieves a kernel-level speedup of \textbf{$2.88\times$} over cuBLAS and a \textbf{$2.02 \times$} throughput improvement compared to TensorRT-LLM from an end-to-end framework perspective.

High computational power and the availability of large datasets have supported the development of Foundational Models. They are a new emerging technique widely used in Generative Artificial Intelligence, characterized by their scalability and their use in Transfer Learning. The enormous and heterogeneous amounts of data used in their initial training phase, known as pre-training, give them a higher generalization capacity than any other specific model, constituting a solid base that can be adapted or adjusted to a wide range of tasks, increasing their applicability. This study proposes LLIAM, the Llama Lora-Integrated Autorregresive Model. Low-Rank Adaptations are used to enhance the knowledge of the model with diverse time series datasets, known as the fine-tuning phase. To illustrate the capabilities of our proposal, two sets of experiments have been carried out that obtained favorable and promising results with lower training times than other Deep Learning approaches. With this work, we also encourage the use of available resources (such as these pre-trained models) to avoid unnecessary and costly training, narrowing the gap between the goals of traditional Artificial Intelligence and those specified by the definition of Green Artificial Intelligence.

Traditional Retrieval-Augmented Generation (RAG) methods are limited by their reliance on a fixed number of retrieved documents, often resulting in incomplete or noisy information that undermines task performance. Although recent adaptive approaches alleviated these problems, their application in intricate and real-world multimodal tasks remains limited. To address these, we propose a new approach called Self-adaptive Multimodal Retrieval-Augmented Generation (SAM-RAG), tailored specifically for multimodal contexts. SAM-RAG not only dynamically filters relevant documents based on the input query, including image captions when needed, but also verifies the quality of both the retrieved documents and the output. Extensive experimental results show that SAM-RAG surpasses existing state-of-the-art methods in both retrieval accuracy and response generation. By further ablation experiments and effectiveness analysis, SAM-RAG maintains high recall quality while improving overall task performance in multimodal RAG task. Our codes are available at https://github.com/SAM-RAG/SAM_RAG.

Recent studies in Retrieval-Augmented Generation (RAG) have investigated extracting evidence from retrieved passages to reduce computational costs and enhance the final RAG performance, yet it remains challenging. Existing methods heavily rely on heuristic-based augmentation, encountering several issues: (1) Poor generalization due to hand-crafted context filtering; (2) Semantics deficiency due to rule-based context chunking; (3) Skewed length due to sentence-wise filter learning. To address these issues, we propose a model-based evidence extraction learning framework, SEER, optimizing a vanilla model as an evidence extractor with desired properties through self-aligned learning. Extensive experiments show that our method largely improves the final RAG performance, enhances the faithfulness, helpfulness, and conciseness of the extracted evidence, and reduces the evidence length by 9.25 times. The code will be available at https://github.com/HITsz-TMG/SEER.

The utility of synthetic data to enhance pretraining data quality and hence to improve downstream task accuracy has been widely explored in recent large language models (LLMs). Yet, these approaches fall inadequate in complex, multi-hop and mathematical reasoning tasks as the synthetic data typically fails to add complementary knowledge to the existing raw corpus. In this work, we propose a novel large-scale and diverse Math Informed syNthetic Dialogue (MIND) generation method that improves the mathematical reasoning ability of LLMs. Specifically, using MIND, we generate synthetic conversations based on OpenWebMath (OWM), resulting in a new math corpus, MIND-OWM. Our experiments with different conversational settings reveal that incorporating knowledge gaps between dialog participants is essential for generating high-quality math data. We further identify an effective way to format and integrate synthetic and raw data during pretraining to maximize the gain in mathematical reasoning, emphasizing the need to restructure raw data rather than use it as-is. Compared to pretraining just on raw data, a model pretrained on MIND-OWM shows significant boost in mathematical reasoning (GSM8K: +13.42%, MATH: +2.30%), including superior performance in specialized knowledge (MMLU: +4.55%, MMLU-STEM: +4.28%) and general purpose reasoning tasks (GENERAL REASONING: +2.51%).

Table processing, a key task in natural language processing, has significantly benefited from recent advancements in language models (LMs). However, the capabilities of LMs in table-to-text generation, which transforms structured data into coherent narrative text, require an in-depth investigation, especially with current open-source models. This study explores the effectiveness of various in-context learning strategies in LMs across benchmark datasets, focusing on the impact of providing examples to the model. More importantly, we examine a real-world use case, offering valuable insights into practical applications. To complement traditional evaluation metrics, we employ a large language model (LLM) self-evaluation approach using chain-of-thought reasoning and assess its correlation with human-aligned metrics like BERTScore. Our findings highlight the significant impact of examples in improving table-to-text generation and suggest that, while LLM self-evaluation has potential, its current alignment with human judgment could be enhanced. This points to the need for more reliable evaluation methods.

Pretraining robust vision or multimodal foundation models (e.g., CLIP) relies on large-scale datasets that may be noisy, potentially misaligned, and have long-tail distributions. Previous works have shown promising results in augmenting datasets by generating synthetic samples. However, they only support domain-specific ad hoc use cases (e.g., either image or text only, but not both), and are limited in data diversity due to a lack of fine-grained control over the synthesis process. In this paper, we design a \emph{controllable} image-text synthesis pipeline, CtrlSynth, for data-efficient and robust multimodal learning. The key idea is to decompose the visual semantics of an image into basic elements, apply user-specified control policies (e.g., remove, add, or replace operations), and recompose them to synthesize images or texts. The decompose and recompose feature in CtrlSynth allows users to control data synthesis in a fine-grained manner by defining customized control policies to manipulate the basic elements. CtrlSynth leverages the capabilities of pretrained foundation models such as large language models or diffusion models to reason and recompose basic elements such that synthetic samples are natural and composed in diverse ways. CtrlSynth is a closed-loop, training-free, and modular framework, making it easy to support different pretrained models. With extensive experiments on 31 datasets spanning different vision and vision-language tasks, we show that CtrlSynth substantially improves zero-shot classification, image-text retrieval, and compositional reasoning performance of CLIP models.

This paper presents a novel approach termed Layer-of-Thoughts Prompting (LoT), which utilizes constraint hierarchies to filter and refine candidate responses to a given query. By integrating these constraints, our method enables a structured retrieval process that enhances explainability and automation. Existing methods have explored various prompting techniques but often present overly generalized frameworks without delving into the nuances of prompts in multi-turn interactions. Our work addresses this gap by focusing on the hierarchical relationships among prompts. We demonstrate that the efficacy of thought hierarchy plays a critical role in developing efficient and interpretable retrieval algorithms. Leveraging Large Language Models (LLMs), LoT significantly improves the accuracy and comprehensibility of information retrieval tasks.