Related papers: Reqo: A Comprehensive Learning-Based Cost Model fo…
While Large Language Models (LLMs) have significantly advanced code generation efficiency, they face inherent challenges in balancing performance and inference costs across diverse programming tasks. Dynamically selecting the optimal LLM…
In information retrieval, large language models (LLMs) have demonstrated remarkable potential in text reranking tasks by leveraging their sophisticated natural language understanding and advanced reasoning capabilities. However,…
Large language models (LLMs) have recently demonstrated their impressive ability to provide context-aware responses via text. This ability could potentially be used to predict plausible solutions in sequential decision making tasks…
The complexities of table structures and question logic make table-based question answering (TQA) tasks challenging for Large Language Models (LLMs), often requiring task simplification before solving. This paper reveals that the reasoning…
Answering complex logical queries on incomplete knowledge graphs is a challenging task, and has been widely studied. Embedding-based methods require training on complex queries, and cannot generalize well to out-of-distribution query…
Long-horizon tasks requiring multi-step reasoning and dynamic re-planning remain challenging for large language models (LLMs). Sequential prompting methods are prone to context drift, loss of goal information, and recurrent failure cycles,…
Large language models (LLMs) achieve state-of-the-art accuracy on complex reasoning tasks by generating multiple chain-of-thought (CoT) traces, but using a fixed token budget per query leads to over-computation on easy inputs and…
Chain-of-thought has been proven essential for enhancing the complex reasoning abilities of Large Language Models (LLMs), but it also leads to high computational costs. Recent advances have explored the method to route queries among…
Efficient data processing is increasingly vital, with query optimizers playing a fundamental role in translating SQL queries into optimal execution plans. Traditional cost-based optimizers, however, often generate suboptimal plans due to…
Large language model (LLM)-based search agents have proven promising for addressing knowledge-intensive problems by incorporating information retrieval capabilities. Existing works largely focus on optimizing the reasoning paradigms of…
External memory systems are pivotal for enabling Large Language Model (LLM) agents to maintain persistent knowledge and perform long-horizon decision-making. Existing paradigms typically follow a two-stage process: computationally expensive…
With the breakthroughs in large language models (LLMs), query generation techniques that expand documents and queries with related terms are becoming increasingly popular in the information retrieval field. Such techniques have been shown…
LLM-guided compiler optimization has recently shown promise, but existing approaches rely on a single large LLM throughout search, making them expensive and excluding smaller models. We pose the research question: whether heterogeneous LLMs…
Pre-trained large multi-modal models (LMMs) exploit fine-tuning to adapt diverse user applications. Nevertheless, fine-tuning may face challenges due to deactivated sensors (e.g., cameras turned off for privacy or technical issues),…
The remarkable performance of Large Language Models (LLMs) has inspired many applications, which often necessitate edge-cloud collaboration due to connectivity, privacy, and cost considerations. Traditional methods primarily focus on…
Effective decision-making in Large Language Models (LLMs) is essential for handling intricate tasks. However, existing approaches prioritize performance but often overlook the balance between effectiveness and computational cost. To address…
Lakehouse systems enable the same data to be queried with multiple execution engines. However, selecting the engine best suited to run a SQL query still requires a priori knowledge of the query computational requirements and an engine…
Training Large Language Models (LLMs) for chain-of-thought reasoning presents a significant challenge: supervised fine-tuning on a single "golden" rationale hurts generalization as it penalizes equally valid alternatives, whereas…
Retrieval-augmented generation (RAG), which combines large language models (LLMs) with retrievals from external knowledge databases, is emerging as a popular approach for reliable LLM serving. However, efficient RAG serving remains an open…
Large language models (LLMs) have exhibited extraordinary performance in a variety of tasks while it remains challenging for them to solve complex multi-step tasks as agents. In practice, agents sensitive to the outcome of certain key steps…