21 accepted papers
Reinforcement Learning from Human Feedback (RLHF) is the standard method to align Large Language Models (LLMs) with human preferences. In this work, we introduce alignment tampering, a potential vulnerability where the LLM undergoing alignment influences the preference dataset, causing RLHF to ampli…
Language models remain vulnerable to prompt injection attacks despite extensive safety training. We trace this failure to role confusion: models assign roles based on how text sounds, not where it actually comes from. We design novel role probes to capture how models internally identify “who is spea…
As LLMs increasingly impact society, their ability to represent diverse perspectives is critical. However, recent studies reveal that alignment algorithms such as RLHF and DPO significantly reduce the diversity of LLM outputs. Not only do aligned LLMs generate text with repetitive structure and wor…
Large Language Model (LLM) agents have demonstrated impressive capabilities for social interaction and are increasingly being deployed in situations where they might engage with both human and artificial agents. These interactions represent a critical frontier for LLM-based agents, yet existing eval…
In practice, preference learning from human feedback depends on incomplete data with hidden context. Hidden context refers to data that affects the feedback received, but which is not represented in the data used to train a preference model. This captures common issues of data collection, such as ha…
Multi-agent AI research promises a path to develop human-like and human-compatible intelligent technologies that complement the solipsistic view of other approaches, which mostly do not consider interactions between agents. Aiming to make progress in this direction, the Melting Pot contest 2023 focu…
Neural language models (LMs) can be used to evaluate the truth of factual statements in two ways: they can be either queried for statement probabilities, or probed for internal representations of truthfulness. Past work has found that these two procedures sometimes disagree, and that probes tend to…
Interpretable AI tools are often motivated by the goal of understanding model behavior in out-of-distribution (OOD) contexts. Despite the attention this area of study receives, there are comparatively few cases where these tools have identified previously unknown bugs in models. We argue that this i…
The content that a recommender system (RS) shows to users influences them. Therefore, when choosing a recommender to deploy, one is implicitly also choosing to induce specific internal states in users. Even more, systems trained via long-horizon optimization will have direct incentives to manipulate…
From the earliest years of our lives, humans use language to express our beliefs and desires. Being able to talk to artificial agents about our preferences would thus fulfill a central goal of value alignment. Yet today, we lack computational models explaining such language use. To address this chal…
The literature on adversarial attacks in computer vision typically focuses on pixel-level perturbations. These tend to be very difficult to interpret. Recent work that manipulates the latent representations of image generators to create "feature-level" adversarial perturbations gives us an opportuni…
While modern policy optimization methods can do complex manipulation from sensory data, they struggle on problems with extended time horizons and multiple sub-goals. On the other hand, task and motion planning (TAMP) methods scale to long horizons but they are computationally expensive and need to p…
AI systems often rely on two key components: a specified goal or reward function and an optimization algorithm to compute the optimal behavior for that goal. This approach is intended to provide value for a principal: the user on whose behalf the agent acts. The objectives given to these ag…
Our goal is for AI systems to correctly identify and act according to their human user’s objectives. Cooperative Inverse Reinforcement Learning (CIRL) formalizes this value alignment problem as a two-player game between a human and robot, in which only the human knows the parameters of the reward fu…
Designing a good reward function is essential to robot planning and reinforcement learning, however it can be both challenging and frustrating. The reward needs to work across multiple different environments, and that often requires many iterations of tuning. We introduce a novel divide-and-conquer…
Autonomous agents optimize the reward function we give them. What they don't know is how hard it is for us to design a reward function that actually captures what we want. When designing the reward, we might think of some specific training scenarios, and make sure that the reward will lead to the r…
For an autonomous system to be helpful to humans and to pose no unwarranted risks, it needs to align its values with those of the humans in its environment in such a way that its actions contribute to the maximization of value for the humans. We propose a formal definition of the value alignment pro…
Tasks in mobile manipulation planning often require thousands of individual motions to complete. Such tasks require reasoning about complex goals as well as the feasibility of movements in configuration space. In discrete representations, planning complexity is exponential in the length of the plan.
We consider the problem of refining an abstract task plan into a motion trajectory. Task and motion planning is a hard problem that is essential to long-horizon mobile manipulation. Many approaches divide the problem into two steps: a search for a task plan and task plan refinement to find a feasibl…
We consider the problem of learning from demonstrations to manipulate deformable objects. Recent work [1], [2], [3] has shown promising results that enable robotic manipulation of deformable objects through learning from demonstrations. Their approach is able to generalize from a single demonstratio…
The execution of long-horizon tasks under uncertainty is a fundamental challenge in robotics. Recent approaches have made headway on these tasks with an integration of task and motion planning. In this paper, we present Interfaced Belief Space Planning (IBSP): a modular approach to task and motion p…