arXiv AI

LEBGen: An LLM-Enhanced Bayesian Network Framework for Few-Shot Travel Survey Data Generation

arXiv AI
Aug 25

Benchmarking Retrieval-Augmented Generation Strategies for Large Language Model-Based Travel Mode Choice Prediction

The paper evaluates how Retrieval-Augmented Generation (RAG) can improve Large Language Model (LLM) predictions of travel mode choice. Four retrieval strategies—basic RAG, balanced retrieval, cross‑encoder re‑ranking, and a combination of balanced retrieval with cross‑encoder—are tested on three LLMs (GPT‑4o, o4‑mini, o3) using 2023 Puget Sound travel survey data. Results show that RAG boosts accuracy across models, with GPT‑4o plus balanced retrieval and cross‑encoder achieving 80.8% accuracy, surpassing traditional statistical and machine learning baselines and demonstrating strong zero‑shot transfer.

By Yiming Xu, Junfeng Jiao
arXiv Machine Learning
Aug 24

Fine-tuning LLMs for Tourist Trajectory Prediction using Field Experiment Data

The paper demonstrates that fine‑tuning large language models (LLMs) on local tourist trajectory data can predict visitor movements under varying conditions. Using 566 trajectories from Wakayama Castle Park, Japan, the authors fine‑tuned Llama‑3.1‑8B, achieving 49.1% accuracy for next point‑of‑interest predictions and maintaining strong performance even on undersampled scenarios such as rainy days. This shows that LLMs can serve as high‑fidelity, context‑aware behavior models for tourist prediction and enable counterfactual analysis of mobility interventions.

By Tatsuya Amano, Hirozumi Yamaguchi
arXiv Machine Learning
Aug 27

Neural-Bayesian Structure Learning for Discrete Choice Modeling

Neural-Bayesian Structure Learning (Neural-BSL) integrates differentiable structure learning with random-utility discrete choice estimation in a single differentiable framework. It keeps observed choices outside the graph to avoid distortion, learns attribute interactions through a structure-weighted network, and propagates interventions by updating attributes in topological order before recomputing utilities and choice probabilities. Evaluations on Seoul stated-preference and London revealed-preference data show Neural-BSL matches conventional benchmarks in predictive performance while uncovering behaviorally coherent dependency structures and revealing downstream traveler and trip adjustments under policy scenarios.

By Hyunsoo Yun, Eun Hak Lee, Jiaru Zhang, Ziran Wang, Eui-Jin Kim
arXiv Computation and Language
Oct 15

AdaptFuse: Training-Free Sequential Preference Inference via Externalized Bayesian Computation

arXiv:2604.03925v2 Announce Type: replace Abstract: Large language models (LLMs) struggle to accumulate evidence across multiple rounds of user interactions, failing to update their beliefs in a mann...

By Fangzhou Lin, Zilin Dai, Shuo Xing, Peiran Li, Siyuan Yang, Qianwen Ge, Kazunori Yamada, Yang Zhou, Ziming Zhang, Haichong Zhang, Zhengzhong Tu
arXiv Machine Learning
Sep 22

CALM: A Calibrated LLM Choice Network Framework for Activity-Based Traveler Simulation

CALM is a reproducible hybrid framework that combines an optional large language model (LLM) activity planner with calibrated stochastic choice, shared network feedback, memory and habit, typed feasibility checks, and deterministic offline replay. It executes a closed traveler‑day loop and evaluates each generative module against an empirical, reproducible baseline, using the 2024 New York City Citywide Mobility Survey data. The framework demonstrates significant improvements in mode‑choice accuracy, quantifies trade‑offs through live‑LLM ablation, and supports controlled stress testing and deterministic replay of downstream simulations.

By Yezhou Cheng
arXiv AI
Sep 17

Extracting Probabilistic Knowledge from Large Language Models for Bayesian Network Parameterization

The paper investigates how Large Language Models can be used to approximate domain expert priors for Bayesian Networks by extracting probabilistic knowledge about real‑world events. Experiments on eighty publicly available networks across domains such as healthcare and finance show that LLM‑derived conditional probabilities outperform random, uniform, and next‑token baselines. The authors also demonstrate that these LLM‑generated priors can refine data‑driven distributions, especially when data is scarce, and provide the first comprehensive baseline for evaluating LLM performance in probabilistic knowledge extraction.

By Aliakbar Nafar, Kristen Brent Venable, Zijun Cui, Parisa Kordjamshidi
arXiv AI
Oct 19

Towards Adaptive and Real-Survey-Aligned Simulated Urban Mobility Behaviour of Generative Agents

The paper presents an agent‑based model of daily multimodal mobility in Toulouse, comparing fifteen decision‑making approaches—including generative agents (GAs) with minimal and tuned prompts, simple baselines, survey‑fitted models, and a typed classifier—against real household travel survey data. Results show that GAs with tuned prompts approximate the modal split of a simulated day without disruptions but fall short on trip‑by‑trip accuracy, while the Jev‑1.13 TypeSafe classifier performs surprisingly well, indicating that generating output text is not essential. The study highlights the potential and current limitations of generative agent‑based modelling for urban mobility.

By Yves Bru, Kamaldeep Singh Oberoi, Benoit Gaudou