Papers
Efficient Switchable Safety Control in LLMs via Magic-Token-Guided Co-Training
Jianfeng Si, Lin Sun, Zhewen Tan et al.
EASE: Practical and Efficient Safety Alignment for Small Language Models
Haonan Shi, Guoli Wang, Tu Ouyang et al.
Tight Robustness Certification Through the Convex Hull of ℓ₀ Attacks
Yuval Shapira, Dana Drachsler-Cohen
Detecting Compute Structuring in AI Governance Is Likely Feasible
Emmanouil Seferis, Timothy Fist
Polarity-Aware Probing for Quantifying Latent Alignment in Language Models
Sabrina Sadiekh, Elena Ericheva, Chirag Agarwal
Mind the Gap: Quantifying and Aligning Human-AI Visual Attention for Accident Anticipation
Hoe Sung Ryu, Christian Wallraven
Confirmation Bias: A Challenge for Scalable Oversight
Gabriel Recchia, Chatrik Singh Mangat, Jinu Nyachhyon et al.
FindTheFlaws: Annotated Errors for Detecting Flawed Reasoning and Scalable Oversight Research
Gabriel Recchia, Chatrik Singh Mangat, Issac Li et al.
Chain-of-Thought Driven Adversarial Scenario Extrapolation for Robust Language Models
Md Rafi Ur Rashid, Vishnu Asutosh Dasu, Ye Wang et al.
Backdoor Attacks on Open Vocabulary Object Detectors via Multi-Modal Prompt Tuning
Ankita Raj, Chetan Arora
Towards Benchmarking Privacy Vulnerabilities in Selective Forgetting with Large Language Models
Wei Qian, Chenxu Zhao, Yangyi Li et al.
Beyond I’m Sorry, I Can’t: Dissecting Large-Language-Model Refusal
Nirmalendu Prakash, Yeo Wei Jie, Amir Abdullah et al.
AdvBDGen: A Robust Framework for Generating Adaptive and Stealthy Backdoors in LLM Alignment
Pankayaraj Pathmanathan, Udari Madhushani Sehwag, Michael-Andrei Panaitescu-Liess et al.
Refine and Align: Confidence Calibration Through Multi-Agent Interaction in VQA
Ayush Pandey, Jai Bardhan, Ishita Jain et al.
LieCraft: A Multi-Agent Framework for Evaluating Deceptive Capabilities in Language Models
Matthew Lyle Olson, Neale Ratzlaff, Musashi Hinck et al.
Realist and Pluralist Conceptions of Intelligence and Their Implications on AI Research
Ninell Oldenburg, Ruchira Dhar, Anders Søgaard
CTPD: Cross Tokenizer Preference Distillation
Truong Nguyen, Phi Van Dat, Ngan Nguyen et al.
A Tale of Two Identities: An Ethical Audit of AI-Crafted Synthetic Personas
Pranav Narayanan Venkit, Jiayi Li, Yingfan Zhou et al.
Quiet Feature Learning in Algorithmic Tasks
Prudhviraj Naidu, Zixian Wang, Leon Bergen et al.
SharedRep-RLHF: A Shared Representation Approach to RLHF with Diverse Preferences
Arpan Mukherjee, Marcello Bullo, Deniz Gündüz
Aligning Machiavellian Agents: Behavior Steering via Test-Time Policy Shaping
Dena Mujtaba, Brian Hu, Anthony Hoogs et al.
STACK: Adversarial Attacks on LLM Safeguard Pipelines
Ian R. McKenzie, Oskar John Hollinsworth, Tom Tseng et al.
Misalignment from Treating Means as Ends
Henrik Marklund, Alex Infanger, Benjamin Van Roy
DETONATE – A Benchmark for Text-to-Image Alignment and Kernelized Direct Preference Optimization
Renjith Prasad Kaippilly Mana, Abhilekh Borah, Hasnat Md Abdullah et al.