AgenticSum: An Agentic Inference-Time Framework for Faithful Clinical Text Summarization

Research Summary

Contribution Summary

• Large language models (LLMs) offer substantial promise for automating clinical text summarization, yet maintaining factual consistency remains challenging due to the length, noise, and heterogeneity of clinical documentation.
• We present AgenticSum, an inference-time, agentic framework that separates context selection, generation, verification, and targeted correction to reduce hallucinated content.
• The framework decomposes summarization into coordinated stages that compress task-relevant context, generate an initial draft, identify weakly supported spans using internal attention grounding signals, and selectively revise flagged conten

Why It Matters For Eval

• We present AgenticSum, an inference-time, agentic framework that separates context selection, generation, verification, and targeted correction to reduce hallucinated content.
• We evaluate AgenticSum on two public datasets, using reference-based metrics, LLM-as-a-judge assessment, and human evaluation.

Related Papers

• Distributional Vision-Language Alignment by Cauchy-Schwarz Divergence Embedding Neighbor
• Why Diffusion Language Models Struggle with Truly Parallel (Non-Autoregressive) Decoding? Embedding Neighbor
• A Mixture-of-Experts Model for Multimodal Emotion Recognition in Conversations Embedding Neighbor
• EpidemIQs: Prompt-to-Paper LLM Agents for Epidemic Modeling and Analysis Embedding Neighbor
• Reasoning Up the Instruction Ladder for Controllable Language Models Embedding Neighbor
• Large Language Models are Algorithmically Blind Embedding Neighbor
• Cost-of-Pass: An Economic Framework for Evaluating Language Models Embedding Neighbor
• Mixture-of-Experts as Soft Clustering: A Dual Jacobian-PCA Spectral Geometry Perspective Embedding Neighbor
• A Diversity Diet for a Healthier Model: A Case Study of French ModernBERT Embedding Neighbor
• Think$^{2}$: Grounded Metacognitive Reasoning in Large Language Models Tag Overlap
• Benchmarking Large Language Models on Answering and Explaining Challenging Medical Questions Tag Overlap
• The Subjectivity of Respect in Police Traffic Stops: Modeling Community Perspectives in Body-Worn Camera Footage Tag Overlap