Benchmarking Contextual Understanding for In-Car Conversational Systems

In-Car Conversational Question Answering (ConvQA) systems significantly enhance user experience by enabling seamless voice interactions. However, assessing their accuracy and reliability remains a challenge. This paper explores the use of Large Language Models (LLMs) alongside advanced prompting techniques and agent-based methods to evaluate the extent to which ConvQA system responses adhere to user utterances. The focus lies on contextual understanding and the ability to provide accurate venue recommendations considering user constraints and situational context. To evaluate utterance-response coherence using an LLM, we synthetically generate user utterances accompanied by correct and modified failure-containing system responses. We use input-output, chain-of-thought, self-consistency prompting, and multi-agent prompting techniques with 13 reasoning and non-reasoning LLMs of varying sizes and providers, including OpenAI, DeepSeek, Mistral AI, and Meta. We evaluate our approach on a case study involving restaurant recommendations. The most substantial improvements occur for small non-reasoning models when applying advanced prompting techniques, particularly multi-agent prompting. However, reasoning models consistently outperform non-reasoning models, with the best performance achieved using single-agent prompting with self-consistency. Notably, DeepSeek-R1 reaches an F1-score of 0.99 at a cost of 0.002 USD per request. Overall, the best balance between effectiveness and cost-time efficiency is reached with the non-reasoning model DeepSeek-V3. Our findings show that LLM-based evaluation offers a scalable and accurate alternative to traditional human evaluation for benchmarking contextual understanding in ConvQA systems.

UnHiPPO: Uncertainty-aware Initialization for State Space Models

State space models are emerging as a dominant model class for sequence problems with many relying on the HiPPO framework to initialize their dynamics. However, HiPPO fundamentally assumes data to be noise-free; an assumption often violated in practice. We extend the HiPPO theory with measurement noise and derive an uncertainty-aware initialization for state space model dynamics. In our analysis, we interpret HiPPO as a linear stochastic control problem where the data enters as a noise-free control signal. We then reformulate the problem so that the data become noisy outputs of a latent system and arrive at an alternative dynamics initialization that infers the posterior of this latent system from the data without increasing runtime. Our experiments show that our initialization improves the resistance of state-space models to noise both at training and inference time. Find our implementation at https://cs.cit.tum.de/daml/unhippo.

Unfolding Time: Generative Modeling for Turbulent Flows in 4D

A recent study in turbulent flow simulation demonstrated the potential of generative diffusion models for fast 3D surrogate modeling. This approach eliminates the need for specifying initial states or performing lengthy simulations, significantly accelerating the process. While adept at sampling individual frames from the learned manifold of turbulent flow states, the previous model lacks the capability to generate sequences, hindering analysis of dynamic phenomena. This work addresses this limitation by introducing a 4D generative diffusion model and a physics-informed guidance technique that enables the generation of realistic sequences of flow states. Our findings indicate that the proposed method can successfully sample entire subsequences from the turbulent manifold, even though generalizing from individual frames to sequences remains a challenging task. This advancement opens doors for the application of generative modeling in analyzing the temporal evolution of turbulent flows, providing valuable insights into their complex dynamics.