Deterministic RAG: A Drop-in Replacement for GraphRAG’s Unstable Planning

Recent advancements in Large Reasoning Models (LRMs) have shown impressive performance in specialized reasoning tasks. However, a systematic evaluation reveals that acquiring deliberative reasoning capabilities significantly reduces foundational capabilities, leading to declines in helpfulness and harmlessness, along with increased inference costs. Adaptive reasoning methods can alleviate these drawbacks, highlighting the need for more versatile LRMs.

The article introduces In-N-Out, a novel dataset designed for tool agents that utilize large language models (LLMs) to interact with external APIs. As tasks grow more complex, these agents often struggle to identify and sequence the correct APIs. In-N-Out addresses this by converting API documentation into a structured graph that captures dependencies, significantly enhancing performance in tool retrieval and multi-tool query generation, nearly doubling the effectiveness of LLMs relying solely on documentation.

ToDRE is a new framework designed for effective visual token pruning in large vision-language models (LVLMs). It emphasizes the importance of visual token diversity and task relevance, proposing a two-stage, training-free approach that utilizes a greedy max-sum diversification algorithm. This method aims to enhance inference efficiency by selecting a representative subset of visual tokens rather than simply removing redundant ones.

The study on intrinsic dimension (ID) in large language models (LLMs) reveals its significance in understanding text properties. It highlights that ID is uncorrelated with entropy-based metrics, indicating a distinct measure of geometric complexity. The research also shows genre stratification in ID, with scientific texts having lower ID compared to creative writing, suggesting that LLMs perceive scientific text as simpler. This work utilizes cross-encoder analysis and sparse autoencoders for its findings.

The paper presents a concept called confidential prompting, aimed at securing user prompts from untrusted cloud-hosted large language models (LLMs). It introduces Petridish, a system utilizing confidential computing and a technology named Secure Partitioned Decoding (SPD). Petridish operates within a confidential virtual machine (CVM) to protect LLM parameters and user prompts from external threats, while efficiently managing user requests through a dual-process system.

The paper discusses the exploitative pricing practices in data markets for large language models (LLMs), which often marginalize data providers. It proposes a fairshare pricing mechanism based on data valuation to enhance seller participation and improve data quality. The framework aims to align incentives between buyers and sellers, ensuring optimal outcomes for both parties while maintaining market sustainability.

Larry Summers has resigned from the board of OpenAI following the exposure of his deep connections with Jeffrey Epstein. Summers acknowledged his association with Epstein as a significant error in judgment. This resignation comes amid growing scrutiny over his past associations and public commitments.

OpenAI has launched a free version of ChatGPT specifically designed for teachers. This initiative aims to provide educators with accessible tools to enhance their teaching methods and engage students more effectively. The move is part of OpenAI's broader strategy to support educational professionals in leveraging AI technology.