13 citations · 18 across the 12 of their papers we have counts for
12 papers
Segment-Level Coherence for Robust Harmful Intent Probing in LLMs
Xuanli He, Bilgehan Sel, Faizan Ali +3
Large Language Models (LLMs) are increasingly exposed to adaptive jailbreaking, particularly in high-stakes Chemical, Biological, Radiological, and Nuclear (CBRN) domains. Although…
Trojan-Speak: Bypassing Constitutional Classifiers with No Jailbreak Tax via Adversarial Finetuning
Bilgehan Sel, Xuanli He, Alwin Peng +2
Fine-tuning APIs offered by major AI providers create new attack surfaces where adversaries can bypass safety measures through targeted fine-tuning. We introduce Trojan-Speak, an a…
Reinforcement Learning with Backtracking Feedback
Bilgehan Sel, Vaishakh Keshava, Phillip Wallis +3
Addressing the critical need for robust safety in Large Language Models (LLMs), particularly against adversarial attacks and in-distribution errors, we introduce Reinforcement Lear…
Backtracking for Safety
Bilgehan Sel, Dingcheng Li, Phillip Wallis +3
Large language models (LLMs) have demonstrated remarkable capabilities across various tasks, but ensuring their safety and alignment with human values remains crucial. Current safe…
LLMs Can Plan Only If We Tell Them
Bilgehan Sel, Ruoxi Jia, Ming Jin
Large language models (LLMs) have demonstrated significant capabilities in natural language processing and reasoning, yet their effectiveness in autonomous planning has been under…
Skin-in-the-Game: Decision Making via Multi-Stakeholder Alignment in LLMs
Bilgehan Sel, Priya Shanmugasundaram, Mohammad Kachuee +3
Large Language Models (LLMs) have shown remarkable capabilities in tasks such as summarization, arithmetic reasoning, and question answering. However, they encounter significant ch…
A CMDP-within-online framework for Meta-Safe Reinforcement Learning
Vanshaj Khattar, Yuhao Ding, Bilgehan Sel +2
Meta-reinforcement learning has widely been used as a learning-to-learn framework to solve unseen tasks with limited experience. However, the aspect of constraint violations has no…
Safe and Balanced: A Framework for Constrained Multi-Objective Reinforcement Learning
Shangding Gu, Bilgehan Sel, Yuhao Ding +4
In numerous reinforcement learning (RL) problems involving safety-critical systems, a key challenge lies in balancing multiple objectives while simultaneously meeting all stringent…
Balance Reward and Safety Optimization for Safe Reinforcement Learning: A Perspective of Gradient Manipulation
Shangding Gu, Bilgehan Sel, Yuhao Ding +4
Ensuring the safety of Reinforcement Learning (RL) is crucial for its deployment in real-world applications. Nevertheless, managing the trade-off between reward and safety during e…
A Human-on-the-Loop Optimization Autoformalism Approach for Sustainability
Ming Jin, Bilgehan Sel, Fnu Hardeep +1
This paper outlines a natural conversational approach to solving personalized energy-related problems using large language models (LLMs). We focus on customizable optimization prob…
Algorithm of Thoughts: Enhancing Exploration of Ideas in Large Language Models
Bilgehan Sel, Ahmad Al-Tawaha, Vanshaj Khattar +2
Current literature, aiming to surpass the "Chain-of-Thought" approach, often resorts to external modi operandi involving halting, modifying, and then resuming the generation proces…
On Solution Functions of Optimization: Universal Approximation and Covering Number Bounds
Ming Jin, Vanshaj Khattar, Harshal Kaushik +2
We study the expressibility and learnability of convex optimization solution functions and their multi-layer architectural extension. The main results are: \emph{(1)} the class of…