Token-Supervised Value Models for Enhancing Mathematical Problem-Solving Capabilities of Large Language Modelsby Jung Hyun Lee,…
Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Trainingby Youliang Yuan,…
ChatGPT Doesn’t Trust Chargers Fans: Guardrail Sensitivity in Contextby Victoria R. Li, Yida Chen, Naomi…
Tumor likelihood estimation on MRI prostate data by utilizing k-Space informationby M. Rempe, F. Hörst,…
Detecting Subtle Differences between Human and Model Languages Using Spectrum of Relative Likelihoodby Yang Xu,…
Decoding Decision Reasoning: A Counterfactual-Powered Model for Knowledge Discoveryby Yingying Fang, Zihao Jin, Xiaodan Xing,…
Recite, Reconstruct, Recollect: Memorization in LMs as a Multifaceted Phenomenonby USVSN Sai Prashanth, Alvin Deng,…
Memorizing Documents with Guidance in Large Language Modelsby Bumjin Park, Jaesik ChoiFirst submitted to arxiv…
FastMem: Fast Memorization of Prompt Improves Context Awareness of Large Language Modelsby Junyi Zhu, Shuochen…
Do More Details Always Introduce More Hallucinations in LVLM-based Image Captioning?by Mingqian Feng, Yunlong Tang,…