Unfamiliar Finetuning Examples Control How Language Models Hallucinate

Large language models (LLMs) have a tendency to generate plausible-sounding yet factually incorrect responses, especially when queried on unfamiliar concepts. In this work, we explore the underlying mechanisms that govern how finetuned LLMs hallucinate. Our investigation reveals an interesting pattern: as inputs become more unfamiliar, LLM outputs tend to default towards a ``hedged'' prediction, whose form is determined by how the unfamiliar examples in the finetuning data are supervised. Thus, by strategically modifying these examples' supervision, we can control LLM predictions for unfamiliar inputs (e.g., teach them to say ``I don't know''). Based on these principles, we develop an RL approach that more reliably mitigates hallucinations for long-form generation tasks, by tackling the challenges presented by reward model hallucinations. We validate our findings with a series of controlled experiments in multiple-choice QA on MMLU, as well as long-form biography and book/movie plot generation tasks.

Hacking Predictors Means Hacking Cars: Using Sensitivity Analysis to Identify Trajectory Prediction Vulnerabilities for Autonomous Driving Security

Adversarial attacks on learning-based trajectory predictors have already been demonstrated. However, there are still open questions about the effects of perturbations on trajectory predictor inputs other than state histories, and how these attacks impact downstream planning and control. In this paper, we conduct a sensitivity analysis on two trajectory prediction models, Trajectron++ and AgentFormer. We observe that between all inputs, almost all of the perturbation sensitivities for Trajectron++ lie only within the most recent state history time point, while perturbation sensitivities for AgentFormer are spread across state histories over time. We additionally demonstrate that, despite dominant sensitivity on state history perturbations, an undetectable image map perturbation made with the Fast Gradient Sign Method can induce large prediction error increases in both models. Even though image maps may contribute slightly to the prediction output of both models, this result reveals that rather than being robust to adversarial image perturbations, trajectory predictors are susceptible to image attacks. Using an optimization-based planner and example perturbations crafted from sensitivity results, we show how this vulnerability can cause a vehicle to come to a sudden stop from moderate driving speeds.

Deep Neural Networks Tend To Extrapolate Predictably

Conventional wisdom suggests that neural network predictions tend to be unpredictable and overconfident when faced with out-of-distribution (OOD) inputs. Our work reassesses this assumption for neural networks with high-dimensional inputs. Rather than extrapolating in arbitrary ways, we observe that neural network predictions often tend towards a constant value as input data becomes increasingly OOD. Moreover, we find that this value often closely approximates the optimal constant solution (OCS), i.e., the prediction that minimizes the average loss over the training data without observing the input. We present results showing this phenomenon across 8 datasets with different distributional shifts (including CIFAR10-C and ImageNet-R, S), different loss functions (cross entropy, MSE, and Gaussian NLL), and different architectures (CNNs and transformers). Furthermore, we present an explanation for this behavior, which we first validate empirically and then study theoretically in a simplified setting involving deep homogeneous networks with ReLU activations. Finally, we show how one can leverage our insights in practice to enable risk-sensitive decision-making in the presence of OOD inputs.

Linking vision and motion for self-supervised object-centric perception

Object-centric representations enable autonomous driving algorithms to reason about interactions between many independent agents and scene features. Traditionally these representations have been obtained via supervised learning, but this decouples perception from the downstream driving task and could harm generalization. In this work we adapt a self-supervised object-centric vision model to perform object decomposition using only RGB video and the pose of the vehicle as inputs. We demonstrate that our method obtains promising results on the Waymo Open perception dataset. While object mask quality lags behind supervised methods or alternatives that use more privileged information, we find that our model is capable of learning a representation that fuses multiple camera viewpoints over time and successfully tracks many vehicles and pedestrians in the dataset. Code for our model is available at https://github.com/wayveai/SOCS.

Cost Inference for Feedback Dynamic Games from Noisy Partial State Observations and Incomplete Trajectories

In multi-agent dynamic games, the Nash equilibrium state trajectory of each agent is determined by its cost function and the information pattern of the game. However, the cost and trajectory of each agent may be unavailable to the other agents. Prior work on using partial observations to infer the costs in dynamic games assumes an open-loop information pattern. In this work, we demonstrate that the feedback Nash equilibrium concept is more expressive and encodes more complex behavior. It is desirable to develop specific tools for inferring players' objectives in feedback games. Therefore, we consider the dynamic game cost inference problem under the feedback information pattern, using only partial state observations and incomplete trajectory data. To this end, we first propose an inverse feedback game loss function, whose minimizer yields a feedback Nash equilibrium state trajectory closest to the observation data. We characterize the landscape and differentiability of the loss function. Given the difficulty of obtaining the exact gradient, our main contribution is an efficient gradient approximator, which enables a novel inverse feedback game solver that minimizes the loss using first-order optimization. In thorough empirical evaluations, we demonstrate that our algorithm converges reliably and has better robustness and generalization performance than the open-loop baseline method when the observation data reflects a group of players acting in a feedback Nash game.

Multi-Task Imitation Learning for Linear Dynamical Systems

We study representation learning for efficient imitation learning over linear systems. In particular, we consider a setting where learning is split into two phases: (a) a pre-training step where a shared $k$-dimensional representation is learned from $H$ source policies, and (b) a target policy fine-tuning step where the learned representation is used to parameterize the policy class. We find that the imitation gap over trajectories generated by the learned target policy is bounded by $\tilde{O}\left( \frac{k n_x}{HN_{\mathrm{shared}}} + \frac{k n_u}{N_{\mathrm{target}}}\right)$, where $n_x > k$ is the state dimension, $n_u$ is the input dimension, $N_{\mathrm{shared}}$ denotes the total amount of data collected for each policy during representation learning, and $N_{\mathrm{target}}$ is the amount of target task data. This result formalizes the intuition that aggregating data across related tasks to learn a representation can significantly improve the sample efficiency of learning a target task. The trends suggested by this bound are corroborated in simulation.

Lyapunov Density Models: Constraining Distribution Shift in Learning-Based Control

Learned models and policies can generalize effectively when evaluated within the distribution of the training data, but can produce unpredictable and erroneous outputs on out-of-distribution inputs. In order to avoid distribution shift when deploying learning-based control algorithms, we seek a mechanism to constrain the agent to states and actions that resemble those that it was trained on. In control theory, Lyapunov stability and control-invariant sets allow us to make guarantees about controllers that stabilize the system around specific states, while in machine learning, density models allow us to estimate the training data distribution. Can we combine these two concepts, producing learning-based control algorithms that constrain the system to in-distribution states using only in-distribution actions? In this work, we propose to do this by combining concepts from Lyapunov stability and density estimation, introducing Lyapunov density models: a generalization of control Lyapunov functions and density models that provides guarantees on an agent's ability to stay in-distribution over its entire trajectory.

Inducing Structure in Reward Learning by Learning Features

Reward learning enables robots to learn adaptable behaviors from human input. Traditional methods model the reward as a linear function of hand-crafted features, but that requires specifying all the relevant features a priori, which is impossible for real-world tasks. To get around this issue, recent deep Inverse Reinforcement Learning (IRL) methods learn rewards directly from the raw state but this is challenging because the robot has to implicitly learn the features that are important and how to combine them, simultaneously. Instead, we propose a divide and conquer approach: focus human input specifically on learning the features separately, and only then learn how to combine them into a reward. We introduce a novel type of human input for teaching features and an algorithm that utilizes it to learn complex features from the raw state space. The robot can then learn how to combine them into a reward using demonstrations, corrections, or other reward learning frameworks. We demonstrate our method in settings where all features have to be learned from scratch, as well as where some of the features are known. By first focusing human input specifically on the feature(s), our method decreases sample complexity and improves generalization of the learned reward over a deepIRL baseline. We show this in experiments with a physical 7DOF robot manipulator, as well as in a user study conducted in a simulated environment.

Learning from learning machines: a new generation of AI technology to meet the needs of science

We outline emerging opportunities and challenges to enhance the utility of AI for scientific discovery. The distinct goals of AI for industry versus the goals of AI for science create tension between identifying patterns in data versus discovering patterns in the world from data. If we address the fundamental challenges associated with "bridging the gap" between domain-driven scientific models and data-driven AI learning machines, then we expect that these AI models can transform hypothesis generation, scientific discovery, and the scientific process itself.

Incorporating Data Uncertainty in Object Tracking Algorithms

Methodologies for incorporating the uncertainties characteristic of data-driven object detectors into object tracking algorithms are explored. Object tracking methods rely on measurement error models, typically in the form of measurement noise, false positive rates, and missed detection rates. Each of these quantities, in general, can be dependent on object or measurement location. However, for detections generated from neural-network processed camera inputs, these measurement error statistics are not sufficient to represent the primary source of errors, namely a dissimilarity between run-time sensor input and the training data upon which the detector was trained. To this end, we investigate incorporating data uncertainty into object tracking methods such as to improve the ability to track objects, and particularly those which out-of-distribution w.r.t. training data. The proposed methodologies are validated on an object tracking benchmark as well on experiments with a real autonomous aircraft.