arXiv AI June 16, 2026 By Miso Choi, Seonga Choi, Mincheol Kwon, Woosung Joung, Jinkyu Kim, Jungbeom Lee

The Truth Stays in the Family: Enhancing Contextual Grounding via Inherited Truthful Heads in Model Lineages

arXiv:2606. 15821v1 Announce Type: cross Abstract: Recent advances in large language models (LLMs) have produced many specialized multimodal LLMs (MLLMs) that share common foundational LLMs, forming distinct model lineages.

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

Jun 10

TruthRL: Incentivizing Truthful LLMs via Reinforcement Learning

arXiv:2509. 25760v2 Announce Type: replace-cross Abstract: While large language models (LLMs) have demonstrated strong performance on factoid question answering, they are still prone to hallucination and untruthful responses, particularly when tasks demand information outside their parametric knowledge.

By Zhepei Wei, Xiao Yang, Kai Sun, Jiaqi Wang, Rulin Shao, Jingxiang Chen, Mohammad Kachuee, Teja Gollapudi, Yiwei Liao, Nicolas Scheffer, Rakesh Wanga, Anuj Kumar, Yu Meng, Wen-tau Yih, Xin Luna Dong

llms nlp reinforcement-learning benchmarks safety

arXiv AI

Sep 15

Testing the Limits of Truth Directions in LLMs

arXiv:2604.03754v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have been shown to encode truth of statements in their activation space along a linear truth direction. Previous...

By Angelos Poulis, Mark Crovella, Evimaria Terzi

llms

arXiv AI

Jul 13

GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs

arXiv:2507. 18043v2 Announce Type: replace-cross Abstract: Inference-time steering methods offer a lightweight alternative to fine-tuning large language models (LLMs) and vision-language models (VLMs) by modifying internal activations at test time without updating model weights.

By Duy Nguyen, Archiki Prasad, Elias Stengel-Eskin, Mohit Bansal

llms fine-tuning multimodal safety

arXiv AI

Jun 9

How Context Shapes Truth: Geometric Transformations of Statement-level Truth Representations in LLMs

arXiv:2601. 06599v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) often encode whether a statement is true as a vector in their residual stream activations.

By Shivam Adarsh, Maria Maistro, Christina Lioma

llms

arXiv AI

Jul 16

Groc-PO: Grounded Context Preference Optimization for Truthful Multimodal LLMs

arXiv:2607. 13712v1 Announce Type: cross Abstract: Despite the rapid progress of Multimodal Large Language Models (MLLMs), they still suffer from untruthfulness issues, such as visual hallucinations, content fabrication, and unfaithful reasoning, which substantially undermine their faithfulness and practical utility.

By Zhixiao Zheng, Zheren Fu, Zhiyuan Yao, Chunxiao Liu, Dongming Zhang, Zhendong Mao

llms reinforcement-learning multimodal safety

arXiv AI

Aug 11

Unified Hallucination Fuzzing for Multimodal Large Language Models

arXiv:2608. 07525v1 Announce Type: cross Abstract: Hallucination remains a persistent challenge for Multimodal Large Language Models (MLLMs), severely limiting their reliability in high-stakes applications.

By Pengfei Zhou, Jiajun Song, Zhiwei Tang, Yixing Ma, Xiaopeng Peng, Donghui Si, Yuhang Xu, Huiqi Song, Yiyuan Miao, Yichen Qian, Weihua Chen, Wangbo Zhao, Bohan Zhuang, Jiasheng Tang, Yang You

llms reinforcement-learning multimodal benchmarks safety

One email a morning, machine-written

Related stories

TruthRL: Incentivizing Truthful LLMs via Reinforcement Learning

Testing the Limits of Truth Directions in LLMs

GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs

How Context Shapes Truth: Geometric Transformations of Statement-level Truth Representations in LLMs

Groc-PO: Grounded Context Preference Optimization for Truthful Multimodal LLMs

Unified Hallucination Fuzzing for Multimodal Large Language Models