GenAI Daily for Practitioners

Executive Summary • Here are the concise bullets for enterprise practitioners: • Can LLMs Score Medical Diagnoses and Clinical Reasoning as well as Expert Panels?: • + LLMs achieve comparable performance to expert panels in medical diagnosis and clinical reasoning tasks. • + Study focuses on four medical domains: breast cancer, lung cancer, heart disease, and diabetes. • + No significant difference in performance between LLMs and expert panels, indicating potential for AI-assisted decision-making. • Adaptive Layer Selection for Layer-Wise Token Pruning in LLM Inference: • + Introduces an adaptive layer selection method for layer-wise token pruning in LLM inference.

Research

• Can LLMs Score Medical Diagnoses and Clinical Reasoning as well as Expert Panels? \ Evaluating medical AI systems using expert clinician panels is costly and slow, motivating the use of large language models (LLMs) as alternative adjudicators. Here, we evaluate an LLM jury composed of three frontier AI models scoring 3333… \ Source • arXiv cs.LG • 13:32
• Adaptive Layer Selection for Layer-Wise Token Pruning in LLM Inference \ Due to the prevalence of large language models (LLMs), key-value (KV) cache reduction for LLM inference has received remarkable attention. Among numerous works that have been proposed in recent years, layer-wise token pruning approaches, w… \ Source • arXiv cs.CL • 18:46
• METER: Evaluating Multi-Level Contextual Causal Reasoning in Large Language Models \ Contextual causal reasoning is a critical yet challenging capability for Large Language Models (LLMs). Existing benchmarks, however, often evaluate this skill in fragmented settings, failing to ensure context consistency or cover the full … \ Source • arXiv cs.CL • 15:47
• Reason Only When Needed: Efficient Generative Reward Modeling via Model-Internal Uncertainty \ Recent advancements in the Generative Reward Model (GRM) have demonstrated its potential to enhance the reasoning abilities of LLMs through Chain-of-Thought (CoT) prompting. Despite these gains, existing implementations of GRM suffer from … \ Source • arXiv cs.CL • 15:43
• Revisiting Compositionality in Dual-Encoder Vision-Language Models: The Role of Inference \ Dual-encoder Vision-Language Models (VLMs) such as CLIP are often characterized as bag-of-words systems due to their poor performance on compositional benchmarks. We argue that this limitation may stem less from deficient representations t… \ Source • arXiv cs.CL • 12:51
• CausalEmbed: Auto-Regressive Multi-Vector Generation in Latent Space for Visual Document Embedding \ Although Multimodal Large Language Models (MLLMs) have shown remarkable potential in Visual Document Retrieval (VDR) through generating high-quality multi-vector embeddings, the substantial storage overhead caused by representing a page wi… \ Source • arXiv cs.CL • 08:59
• Rethinking LLM-Driven Heuristic Design: Generating Efficient and Specialized Solvers via Dynamics-Aware Optimization \ Large Language Models (LLMs) have advanced the field of Combinatorial Optimization through automated heuristic generation. Instead of relying on manual design, this LLM-Driven Heuristic Design (LHD) process leverages LLMs to iteratively ge… \ Source • arXiv cs.LG • 19:09
• From Tokens to Layers: Redefining Stall-Free Scheduling for MoE Serving with Layered Prefill \ Large Language Model (LLM) inference in production must meet stringent service-level objectives for both time-to-first-token (TTFT) and time-between-token (TBT) while maximizing throughput under fixed compute, memory, and interconnect budg… \ Source • arXiv cs.LG • 14:39
• Preconditioned Test-Time Adaptation for Out-of-Distribution Debiasing in Narrative Generation \ Although debiased large language models (LLMs) excel at handling known or low-bias prompts, they often fail on unfamiliar and high-bias prompts. We demonstrate via out-of-distribution (OOD) detection that these high-bias prompts cause a di… \ Source • arXiv cs.CL • 18:26
• OccuBench: Evaluating AI Agents on Real-World Professional Tasks via Language Environment Simulation \ AI agents are expected to perform professional work across hundreds of occupational domains (from emergency department triage to nuclear reactor safety monitoring to customs import processing), yet existing benchmarks can only evaluate age… \ Source • arXiv cs.CL • 18:00
• DySCO: Dynamic Attention-Scaling Decoding for Long-Context Language Models \ Understanding and reasoning over long contexts is a crucial capability for language models (LMs). Although recent models support increasingly long context windows, their accuracy often deteriorates as input length grows. In practice, model… \ Source • arXiv cs.CL • 17:31
• Attribution, Citation, and Quotation: A Survey of Evidence-based Text Generation with Large Language Models \ The increasing adoption of large language models (LLMs) has raised serious concerns about their reliability and trustworthiness. As a result, a growing body of research focuses on evidence-based text generation with LLMs, aiming to link mo… \ Source • arXiv cs.CL • 16:22

Big Tech

No items today.

Regulation & Standards

No items today.

Enterprise Practice

No items today.

Open-Source Tooling

No items today.

— Personal views, not IBM. No tracking. Curated automatically; links under 24h old.