Related papers: AOCI: Symbolic-Semantic Indexing for Practical Rep…

Clinical reasoning agents based on large language models (LLMs) aim to automate tasks such as intensive care unit (ICU) monitoring and patient state tracking from electronic health records (EHRs). Existing systems typically rely on manually…

High-quality evaluation benchmarks are pivotal for deploying Large Language Models (LLMs) in Automated Code Review (ACR). However, existing benchmarks suffer from two critical limitations: first, the lack of multi-language support in…

In large-scale image retrieval, many indexing methods have been proposed to narrow down the searching scope of retrieval. The features extracted from images usually are of high dimensions or unfixed sizes due to the existence of key points.…

Large Language Models (LLMs), when paired with prompt-based tasks, have significantly reduced data annotation costs and reliance on human annotators. However, evaluating the quality of their annotations remains challenging in dynamic,…

We introduce SymbolicAI, a versatile and modular framework employing a logic-based approach to concept learning and flow management in generative processes. SymbolicAI enables the seamless integration of generative models with a diverse…

The deployment of large language models (LLMs) in production environments has created an urgent need for observability systems that span the full stack -- from model internals to GPU kernels. Yet existing monitoring approaches address…

Given a large and evolving codebase, the ability to automatically generate holistic, architecture-aware documentation that captures not only individual functions but also cross-file, cross-module, and system-level interactions remains an…

Index recommendation is crucial for optimizing database performance. However, existing heuristic- and learning-based methods often rely on inefficient exhaustive search and estimated costs, leading to low efficiency (due to the vast search…

Rule-based reasoning over natural language input arises in domains where decisions must be auditable and justifiable: clinical protocols specify eligibility criteria in prose, evidence rules define admissibility through textual conditions,…

Large language models have made substantial progress in addressing diverse code-related tasks. However, their adoption is hindered by inconsistencies in generating output due to the lack of real-world, domain-specific information, such as…

Code localization is a cornerstone of autonomous software engineering. Recent advancements have achieved impressive performance on real-world issue benchmarks. However, we identify a critical yet overlooked bias: these benchmarks are…

The application of Artificial Intelligence (AI) in healthcare has been revolutionary, especially with the recent advancements in transformer-based Large Language Models (LLMs). However, the task of understanding unstructured electronic…

Knowledge representation and reasoning are critical challenges in Artificial Intelligence (AI), particularly in integrating neural and symbolic approaches to achieve explainable and transparent AI systems. Traditional knowledge…

Log parsing transforms raw logs into structured templates containing constants and variables. It underpins anomaly detection, failure diagnosis, and other AIOps tasks. Current parsers are mostly reactive and log-centric. They only infer…

Perceiving visual semantics embedded within consecutive characters is a crucial yet under-explored capability for both Large Language Models (LLMs) and Multi-modal Large Language Models (MLLMs). In this work, we select ASCII art as a…

Large reasoning models (LRMs) like OpenAI-o1 have demonstrated impressive long stepwise reasoning capabilities through large-scale reinforcement learning. However, their extended reasoning processes often suffer from knowledge…

Modern search techniques either cannot efficiently incorporate human feedback to refine search results or to express structural or semantic properties of desired code. The key insight of our interactive code search technique ALICE is that…

Training large language models (LLMs) with synthetic reasoning data has become a popular approach to enhancing their reasoning capabilities, while a key factor influencing the effectiveness of this paradigm is the quality of the generated…

Academic research tends to focus on new models for document understanding creating a wide gap in the literature between model definition and running models at production scale. To close that gap, we present a microservice architecture that…

Motivation Modern molecular sequence analysis increasingly relies on automated and robust software tools for interpretation, annotation, and biological insight. The Analysis of Orthologous Collections (AOC) application automates the…