arXiv AI August 26, 2026 By Himanshu Tripathi, Subash Neupane, Shaswata Mitra, Sudip Mittal, Noorbakhsh Amiri Golilarz, Shahram Rahimi

Gated Activation Steering for Reducing Sycophancy & Hallucination in Medical Question Answering

Read the original on arXiv AI →

The paper introduces Gated Activation Steering, an inference-time intervention that jointly mitigates hallucination and sycophancy in medical question answering. By learning separate steering directions from contrastive clinical pairs and applying them to specific attention heads, the method uses behavior‑specific gates to intervene only when needed. Experiments on EHR‑based clinical questions show that the 4‑billion‑parameter model with gated steering outperforms its unsteered counterpart and rivals larger models in resisting user pressure.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI

Aug 5

Quantifying Hallucinations in Language Language Models on Medical Textbooks

arXiv:2603. 09986v3 Announce Type: replace-cross Abstract: Hallucinations, the tendency for large language models to provide responses with factually incorrect and unsupported claims, is a serious problem within natural language processing for which we do not yet have an effective solution to mitigate against.

By Brandon C. Colelough, Davis Bartels, Dina Demner-Fushman

llms nlp benchmarks safety

arXiv Machine Learning

Jul 31

Position, Not Provenance: Separating Reasoning Mediation from Sycophancy in Medical Vision-Language Models

arXiv:2607. 27304v1 Announce Type: new Abstract: Medical vision-language models (VLMs) generate chain-of-thought (CoT) reasoning before answering clinical questions, but whether this reasoning causally influences predictions remains unclear.

By Supratik Bhowal, Subhrajyoti Basu, Aritra Gir Mahanta, Anik Pal Chowdhury

llms multimodal

arXiv AI

Jul 24

Post-Hoc Reasoning in Chain of Thought: Decoding and Steering Pre-Committed Answers

arXiv:2603. 01437v2 Announce Type: replace Abstract: As chain of thought (CoT) has become central to scaling reasoning capabilities in large language models (LLMs), it has also emerged as a promising tool for interpretability, suggesting the opportunity to understand model decisions through verbalized reasoning.

By Kyle Cox, Darius Kianersi, Adri\`a Garriga-Alonso

llms safety

arXiv AI

Jun 10

Recalling Too Well: Sycophancy Evaluation and Mitigation in Memory-Augmented Models

arXiv:2606. 10949v1 Announce Type: new Abstract: Persistent memory systems promise to make LLMs more helpful by storing user beliefs over time.

By Shelly Bensal, Axel Magnuson, Aparna Balagopalan, Daniel M. Bikel

llms benchmarks

arXiv Machine Learning

Jun 2

Resonant Context Anchoring: Decoupling Attention Routing and Signal Gain at Inference Time

arXiv:2606. 01923v1 Announce Type: cross Abstract: Large Language Models (LLMs) frequently exhibit "contextual disregard" when faced with input evidence that conflicts with their internal parametric memory, leading to persistent factual hallucinations.

By Mingkuan Zhao, Yide Gao, Wentao Hu, Suquan Chen, Tianchen Huang, Zhenhua An, Zetao Chang, Xiayu Sun, Yuheng Min

llms efficiency safety

arXiv AI

Jun 8

When Large Language Models Fail in Healthcare: Evaluating Sensitivity to Prompt Variations

arXiv:2606. 07237v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly used in healthcare for tasks such as clinical question answering, diagnosis support, and report summarization.

By Mahdi Alkaeed

llms nlp benchmarks safety

One email a morning, machine-written

Related stories

Quantifying Hallucinations in Language Language Models on Medical Textbooks

Position, Not Provenance: Separating Reasoning Mediation from Sycophancy in Medical Vision-Language Models

Post-Hoc Reasoning in Chain of Thought: Decoding and Steering Pre-Committed Answers

Recalling Too Well: Sycophancy Evaluation and Mitigation in Memory-Augmented Models

Resonant Context Anchoring: Decoupling Attention Routing and Signal Gain at Inference Time

When Large Language Models Fail in Healthcare: Evaluating Sensitivity to Prompt Variations