# STRIDE: Automated Evaluation of Text-to-Trajectory Alignment across Diverse Contexts

arXiv: https://arxiv.org/abs/2609.34799 · HTML: https://mlsanity.com/paper/2609.34799/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 33 of its 65 references that are in the map.
- First posted on arXiv 28 Sep 2026.

## Builds on (most cited first, 30 of 33)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [Large Language Models are not Fair Evaluators](https://mlsanity.com/paper/2305.17926/) (2023)
- [GenEval: An Object-Focused Framework for Evaluating Text-to-Image Alignment](https://mlsanity.com/paper/2310.11513/) (2023)
- [Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks](https://mlsanity.com/paper/1803.10892/) (2018)
- [MotionGPT: Human Motion as a Foreign Language](https://mlsanity.com/paper/2306.14795/) (2023)
- [Evaluating Text-to-Visual Generation with Image-to-Text Generation](https://mlsanity.com/paper/2404.01291/) (2024)
- [TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answering](https://mlsanity.com/paper/2303.11897/) (2023)
- [T2I-CompBench++: An Enhanced and Comprehensive Benchmark for Compositional Text-to-image Generation](https://mlsanity.com/paper/2307.06350/) (2023)
- [EMMA: End-to-End Multimodal Model for Autonomous Driving](https://mlsanity.com/paper/2410.23262/) (2024)
- [Who Validates the Validators? Aligning LLM-Assisted Evaluation of LLM Outputs with Human Preferences](https://mlsanity.com/paper/2404.12272/) (2024)
- [Human Trajectory Forecasting in Crowds: A Deep Learning Perspective](https://mlsanity.com/paper/2007.03639/) (2020)
- [VLP: Vision Language Planning for Autonomous Driving](https://mlsanity.com/paper/2401.05577/) (2024)
- [Language Prompt for Autonomous Driving](https://mlsanity.com/paper/2309.04379/) (2023)
- [TLControl: Trajectory and Language Control for Human Motion Synthesis](https://mlsanity.com/paper/2311.17135/) (2023)
- [Language Conditioned Traffic Generation](https://mlsanity.com/paper/2307.07947/) (2023)
- [DiffTraj: Generating GPS Trajectory with Diffusion Probabilistic Model](https://mlsanity.com/paper/2304.11582/) (2023)
- [MotionFix: Text-Driven 3D Human Motion Editing](https://mlsanity.com/paper/2408.00712/) (2024)
- [SingularTrajectory: Universal Trajectory Predictor Using Diffusion Model](https://mlsanity.com/paper/2403.18452/) (2024)
- [Can Language Beat Numerical Regression? Language-Based Multimodal Trajectory Prediction](https://mlsanity.com/paper/2403.18447/) (2024)
- [trajdata: A Unified Interface to Multiple Human Trajectory Datasets](https://mlsanity.com/paper/2307.13924/) (2023)
- [LG-Traj: LLM Guided Pedestrian Trajectory Prediction](https://mlsanity.com/paper/2403.08032/) (2024)
- [OpenTraj: Assessing Prediction Complexity in Human Trajectories Datasets](https://mlsanity.com/paper/2010.00890/) (2020)
- [Language-Driven Interactive Traffic Trajectory Generation](https://mlsanity.com/paper/2405.15388/) (2024)
- [VisionTrap: Vision-Augmented Trajectory Prediction Guided by Textual Descriptions](https://mlsanity.com/paper/2407.12345/) (2024)
- [Generative Planning with 3D-vision Language Pre-training for End-to-End Autonomous Driving](https://mlsanity.com/paper/2501.08861/) (2025)
- [SocialGen: Modeling Multi-Human Social Interaction with Language Models](https://mlsanity.com/paper/2503.22906/) (2025)
- [LANGTRAJ: Diffusion Model and Dataset for Language-Conditioned Trajectory Simulation](https://mlsanity.com/paper/2504.11521/) (2025)
- [Continuous Locomotive Crowd Behavior Generation](https://mlsanity.com/paper/2504.04756/) (2025)
- [LILAC: Language-Conditioned Object-Centric Optical Flow for Open-Loop Trajectory Generation](https://mlsanity.com/paper/2603.25481/) (2026)

## Abstract (arXiv)

Language-conditioned trajectory generation is here, but its evaluation has not kept pace. Existing pedestrian trajectory metrics compare trajectories with real-world human data. This does not scale to text-to-trajectory generation across diverse contexts, as collecting human trajectories for every scenario is costly and infeasible. Moreover, pedestrian behavior is heterogeneous and context-dependent, with no single metric as the correct answer, and current evaluation frameworks are not transferable to this domain. These challenges make scalable, reliable evaluation difficult. We introduce STRIDE, the first framework for evaluating context alignment between scenario descriptions and pedestrian trajectories. STRIDE addresses these challenges through three design choices. First, we derive our VRDST evaluation protocol from sociological theories to define a complete evaluation space. Second, it decomposes high-level context into scenario-adaptive behavioral questions. Third, every question is resolved against a deterministic measurement tool library that yields reproducible answers. Together, STRIDE enables complete, verifiable, automated, and scalable evaluation across diverse contexts without requiring human trajectory data. We instantiate STRIDE in the crowd domain as STRIDE-Bench, comprising 1K scenarios, 6K behavioral questions, and 11K measurements with calibrated expected answers across 30 real-world maps. Comprehensive human validations show that STRIDE-Bench is consistent with human behavior and judgment, achieving 80% human agreement. We further evaluate several text-to-trajectory models, finding limited context-alignment capability and persistent challenges in fine-grained context conditioning. We believe that the STRIDE framework provides a first step toward principled evaluation of context-aligned pedestrian trajectory generation.