大模型对齐与安全

Knowledge distillation through geometry-aware representational alignment

Prajjwal Bhattarai, Mohammad Amjad, Dmytro Zhylko, Tuka Alhanai

机构 * New York University Abu Dhabi（纽约大学阿布扎赫德分校） ； New York University（纽约大学） ； Tandon School of Engineering（Tandon工程学院） 纠错

专题命中 其他安全 ：alignment(title,abstract)；分类 cs.AI、cs.LG

Enabling Rapid Shared Human-AI Mental Model Alignment via the After-Action Review

Edward Gu, Ho Chit Siu, Melanie Platt, Isabelle Hurley, Jaime Peña, Rohan Paleja

专题命中 其他安全 ：alignment(title,abstract)；分类 cs.AI

Comments Accepted to the Cooperative Multi-Agent Systems Decision-making and Learning:Human-Multi-Agent Cognitive Fusion Workshop at AAAI 2025

Learning to See Before Seeing: Demystifying LLM Visual Priors from Language Pre-training

Junlin Han, Shengbang Tong, David Fan, Yufan Ren, Koustuv Sinha, Philip Torr, Filippos Kokkinos

机构 * Meta Superintelligence Labs（Meta 超智能实验室） ； University of Oxford（牛津大学） 纠错

专题命中 其他安全 ：alignment(abstract)；分类 cs.AI、cs.LG

Comments Project page: https://junlinhan.github.io/projects/lsbs/

Sandbagging in a Simple Survival Bandit Problem

Joel Dyer, Daniel Jarne Ornia, Nicholas Bishop, Anisoara Calinescu, Michael Wooldridge

机构 * University of Oxford（牛津大学） 纠错

专题命中 其他安全 ：safety(abstract)；分类 cs.AI、cs.LG

Comments Forthcoming in the "Reliable ML from Unreliable Data Workshop" at NeurIPS 2025

Cyclic Ablation: Testing Concept Localization against Functional Regeneration in AI

Eduard Kapelko

机构 * Eduard Kapelko（独立研究者） 纠错

专题命中 其他安全 ：safety(abstract)；分类 cs.CL、cs.LG

Comments Code is available at: https://www.kaggle.com/code/kapedalex/cycleablationpublic/

MEDAKA: Construction of Biomedical Knowledge Graphs Using Large Language Models

Asmita Sengupta, David Antony Selby, Sebastian Josef Vollmer, Gerrit Großmann

机构 * Department of Data Science and its Applications, German Research Center for Artificial Intelligence (DFKI GmbH)（数据科学及其应用系，德国人工智能研究中心（DFKI GmbH）） ； Department of Computer Science, University of Kaiserslautern–Landau (RPTU)（计算机科学系，凯撒斯劳滕-兰道大学（RPTU）） 纠错

专题命中 其他安全 ：safety(abstract)；分类 cs.AI

Comments 9 pages, 5 figures, 2 tables

Reinforcement Learning-Guided Chain-of-Draft for Token-Efficient Code Generation

Xunzhu Tang, Iyiola Emmanuel Olatunji, Tiezhu Sun, Jacques Klein, Tegawende F. Bissyande

机构 * University of Luxembourg（卢森堡大学） 纠错

专题命中 其他安全 ：alignment(abstract)；分类 cs.AI

SETR: A Two-Stage Semantic-Enhanced Framework for Zero-Shot Composed Image Retrieval

Yuqi Xiao, Yingying Zhu

机构 * Yuqi Xiao, Yingying Zhu 纠错

专题命中 其他安全 ：alignment(abstract)

Fingerprinting Organic Molecules for the Inverse Design of Two-Dimensional Hybrid Perovskites with Target Energetics

Yongxin Lyu, Yifan Zhou, Yu Zhang, Yang Yang, Bosen Zou, Qiang Weng, Tong Xie, Claudio Cazorla, Jianhua Hao, Jun Yin, Tom Wu

专题命中 其他安全 ：alignment(abstract)