238 stories tagged LLMs · page 7 of 10
A new study compares how different FHIR data serialization formats affect LLM performance in medication reconciliation tasks. The findings highlight significant differences in accuracy across serialization methods.
Researchers propose an explainable AML triage framework using LLMs to handle transaction alerts while mitigating hallucinations and ensuring compliance. The approach emphasizes evidence-constrained decision-making to improve auditability and governance.
Researchers introduce DWTSumm, a Discrete Wavelet Transform (DWT)-based method to enhance LLM summarization of long, domain-specific documents. The approach decomposes text into global and local components, preserving structure and critical details.
DeepSeek-V4 introduces a one-million-token context window, making it the largest available. This breakthrough enables agents to process extensive documents and conversations with unprecedented context retention.
Researchers have developed an autonomous LLM agent that can independently formulate, test, and refine materials science theories. The agent successfully replicated established equations like the Hall-Petch equation and Paris law without human intervention.
A new paper provides a comprehensive review of externalization techniques in LLM agents, focusing on memory and harness engineering. It highlights key advancements and challenges in the field.
Researchers propose TTKV, a temporal-tiered KV cache that prioritizes recent memories in LLMs, improving efficiency for long-context inference. This method mimics human memory systems, offering a more scalable solution than existing approaches.
A new study identifies specific neurons and attention heads in LLMs that encode harmful stereotypes. The research provides tools to locate and potentially mitigate biases in AI models. Researchers used a combination of contrastive neuron activation analysis and attention head tracking to pinpoint bias sources in GPT-2 Small and Llama 3.2.
Researchers propose a new method for evaluating LLMs that considers individual user preferences, moving beyond aggregate benchmarks. This approach uses ELO ratings to rank models based on personal context and needs.
Researchers introduce OThink-SRR1, a framework that improves RAG systems by refining search results and reducing computational costs. The method addresses key challenges in dynamic retrieval for complex reasoning tasks.
Researchers found that 'hallucination neurons' in LLMs generalize across multiple domains, including legal, financial, and scientific contexts. This discovery could improve model reliability and reduce false information generation.
Researchers introduced DW-Bench, a benchmark for evaluating LLMs on data warehouse graph topology reasoning. Experiments show tool-augmented methods outperform static approaches but struggle with complex tasks.
Researchers introduce Lyzr Cognis, a unified memory architecture for conversational AI agents that enables persistent memory and personalization. The system uses a multi-stage retrieval pipeline combining keyword and vector search.
A new study finds that AI agents conducting scientific research often produce results without adhering to traditional scientific reasoning. The research highlights significant gaps in the epistemic norms of AI-driven scientific inquiry. (~50 words)
Researchers introduce a framework to translate natural language into executable formal logic, addressing LLMs' limitations in symbolic reasoning. The NARS-Reasoning-v0.1 benchmark enables evaluation of this neuro-symbolic approach.
Researchers introduce ARES, a new framework to detect and mitigate systemic weaknesses in reinforcement learning from human feedback (RLHF). ARES addresses cases where both the reward model and the core LLM fail simultaneously, a critical vulnerability in current alignment methods.
A curated list of small LLMs optimized for 16GB RAM devices, including Qwen3.5 9B and others. These models balance performance and efficiency for daily use.
Researchers introduce a novel framework that integrates large language models (LLMs) with Random Forests (RF) through reinforcement learning. This method enables iterative feedback between gradient-based and non-differentiable models, enhancing predictive performance.
QU-NLP's approach to the QIAS 2026 shared task leverages multi-stage QLoRA fine-tuning on Qwen3-4B for complex Islamic inheritance reasoning. This method enhances structured reasoning in legal domains with precise fractional calculations and rule-based decisions.
A comprehensive survey explores domain-level data mixing techniques for optimizing large language model pretraining. The research underscores the importance of strategic data composition in improving efficiency and generalization under constrained resources.
Researchers introduced LiFT, a framework that improves large language models' ability to handle longitudinal NLP tasks. The method uses instruction fine-tuning to better track temporal changes in human behavior and opinions.
Researchers propose HalluSAE, a novel method to detect hallucinations in LLMs by modeling them as critical shifts in latent dynamics. This approach addresses the dynamic nature of hallucinations often overlooked by existing methods.
Researchers introduce GoCoMA, a multimodal framework to identify the source of LLM-generated code. This addresses security and licensing concerns by analyzing code stylometry and binary image representations.
Researchers introduce GeoRepEval, a framework to evaluate large language models' robustness to different geometric problem representations. The study highlights that current benchmarks overlook representation invariance, masking potential failures.