相关论文: Adversarial Preference Learning for Robust LLM Ali…

The robustness of modern machine learning (ML) models has become an increasing concern within the community. The ability to subvert a model into making errant predictions using seemingly inconsequential changes to input is startling, as is…

Despite recent efforts in Large Language Model (LLM) safety and alignment, current adversarial attacks on frontier LLMs can still consistently force harmful generations. Although adversarial training has been widely studied and shown to…

Safe reinforcement learning (Safe RL) aims to ensure policy performance while satisfying safety constraints. However, most existing Safe RL methods assume benign environments, making them vulnerable to adversarial perturbations commonly…

Reinforcement Learning (RL) algorithms suffer from the dependency on accurately engineered reward functions to properly guide the learning agents to do the required tasks. Preference-based reinforcement learning (PbRL) addresses that by…

As powerful Large Language Models (LLMs) are now widely used for numerous practical applications, their safety is of critical importance. While alignment techniques have significantly improved overall safety, LLMs remain vulnerable to…

As large language models (LLMs) become more capable, fine-tuning techniques for aligning with human intent are increasingly important. A key consideration for aligning these models is how to most effectively use human resources, or model…

Reinforcement Learning (RL) methods have emerged as a popular choice for training an efficient and effective dialogue policy. However, these methods suffer from sparse and unstable reward signals returned by a user simulator only when a…

Deep Reinforcement Learning (DRL) is a subfield of machine learning for training autonomous agents that take sequential actions across complex environments. Despite its significant performance in well-known environments, it remains…

Learning from human involvement aims to incorporate the human subject to monitor and correct agent behavior errors. Although most interactive imitation learning methods focus on correcting the agent's action at the current state, they do…

Preference-based reinforcement learning (PbRL) has shown impressive capabilities in training agents without reward engineering. However, a notable limitation of PbRL is its dependency on substantial human feedback. This dependency stems…

The fine-tuning of pre-trained language models has a great success in many NLP fields. Yet, it is strikingly vulnerable to adversarial examples, e.g., word substitution attacks using only synonyms can easily fool a BERT-based sentiment…

Traditional (fickle) adversarial examples involve finding a small perturbation that does not change an input's true label but confuses the classifier into outputting a different prediction. Conversely, obstinate adversarial examples occur…

Aligning large language models (LLMs) with human preferences is critical to recent advances in generative artificial intelligence. Reinforcement learning from human feedback (RLHF) is widely applied to achieve this objective. A key step in…

Natural Language Processing (NLP) models based on Machine Learning (ML) are susceptible to adversarial attacks -- malicious algorithms that imperceptibly modify input text to force models into making incorrect predictions. However,…

Preference-based reinforcement learning (PbRL) provides a powerful paradigm to avoid meticulous reward engineering by learning rewards based on human preferences. However, real-time human feedback is hard to obtain in online tasks. Most…

We propose an adversarial deep reinforcement learning (ADRL) algorithm for high-dimensional stochastic control problems. Inspired by the information relaxation duality, ADRL reformulates the control problem as a min-max optimization between…

Aligning large language models (LLMs) with human values is an increasingly critical step in post-training. Direct Preference Optimization (DPO) has emerged as a simple, yet effective alternative to reinforcement learning from human feedback…

Reinforcement Learning from Human Feedback (RLHF) is commonly employed to tailor models to human preferences, especially to improve the safety of outputs from large language models (LLMs). Traditionally, this method depends on selecting…

We study the robustness of reinforcement learning (RL) with adversarially perturbed state observations, which aligns with the setting of many adversarial attacks to deep reinforcement learning (DRL) and is also important for rolling out…

Insensitivity to semantically-preserving variations of prompts (paraphrases) is crucial for reliable behavior and real-world deployment of large language models. However, language models exhibit significant performance degradation when…