ReFactX: Scalable Reasoning with Reliable Facts via Constrained Generation

The paper introduces Group Turn Policy Optimization (GTPO), a novel reinforcement learning algorithm aimed at enhancing the training of Large Language Models (LLMs) for multi-turn Tool-Integrated Reasoning (TIR). GTPO addresses limitations of existing methods like Group Relative Policy Optimization (GRPO) by implementing turn-level reward assignments, return-based advantage estimation, and self-supervised reward shaping, which collectively improve learning signals for complex interactions.

The paper presents ARTER (Adaptive Routing and Targeted Entity Reasoning), a novel approach to Entity Linking (EL) that utilizes large language models (LLMs) without extensive fine-tuning. ARTER combines candidate generation, context-based scoring, adaptive routing, and selective reasoning to improve efficiency. It categorizes contextual mentions into easy and hard cases, processing them with a low-computational linker and targeted LLM reasoning. ARTER outperforms existing methods like ReFinED by up to 4.47% on standard benchmarks.

Large Language Models (LLMs) are advanced linguistic tools that can produce outputs that may sound plausible but are often factually incorrect, a phenomenon known as hallucination. This study introduces a mathematical framework to analyze, quantify, and mitigate these hallucinations. It employs probabilistic modeling and Bayesian uncertainty estimation to develop refined metrics and strategies, including contrastive decoding and retrieval-augmented grounding, aimed at enhancing the reliability of LLMs.

The paper introduces TASA (Teaching According to Students' Aptitude), a personalized mathematics tutoring framework that utilizes Large Language Models (LLMs) to adapt instruction based on students' evolving knowledge and cognitive retention. TASA integrates a structured student persona and event memory to enhance learning by addressing individual proficiency levels and forgetting patterns, aiming to improve the effectiveness of mathematics education.

Large Language Models (LLMs) have shown exceptional ability in text generation but often produce factually incorrect statements, known as 'hallucinations'. This study investigates hallucinations in conversational data across three low-resource languages: Hindi, Farsi, and Mandarin. The analysis of various LLMs, including GPT-3.5 and GPT-4o, reveals that while Mandarin has few hallucinated responses, Hindi and Farsi exhibit significantly higher rates of inaccuracies.

The study presents a data-driven machine learning approach aimed at optimizing the performance of Large Language Model (LLM) adapters in GPU serving environments. It addresses the challenge of maximizing throughput while preventing request starvation by determining the optimal configuration of concurrent and parallel adapters. The introduction of a Digital Twin for LLM-adapter systems facilitates efficient training data generation, with experiments showing a throughput accuracy within 5.1% of real results.

ConInstruct is a benchmark designed to evaluate Large Language Models (LLMs) on their ability to detect and resolve conflicts in user instructions. While many existing assessments focus on adherence to instructions, ConInstruct addresses the often-overlooked scenarios where conflicting constraints arise. Initial evaluations show that proprietary LLMs generally perform well in conflict detection, with DeepSeek-R1 and Claude-4.5-Sonnet achieving the highest F1-scores.

The research introduces Context Cascade Compression (C3), a method designed to tackle the challenges posed by million-level token inputs in long-context tasks for Large Language Models (LLMs). C3 utilizes two LLMs of varying sizes, where a smaller model compresses text into latent tokens, followed by a larger model that decodes this compressed context. Preliminary experiments indicate that C3 achieves a 20x compression ratio with 98% decoding accuracy.