# LETToT: Label-Free Evaluation of Large Language Models On Tourism Using Expert Tree-of-Thought

arXiv: https://arxiv.org/abs/2508.11280 · HTML: https://mlsanity.com/paper/2508.11280/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 4 of its 29 references that are in the map.
- First posted on arXiv 15 Aug 2025.

## Placed in

- LLM reasoning / [Spatial and embodied reasoning](https://mlsanity.com/lr/spatial-and-embodied-reasoning/)

## Builds on (most cited first, 4 of 4)

- [Holistic Evaluation of Language Models](https://mlsanity.com/paper/2211.09110/) (2022)
- [DOTS: Learning to Reason Dynamically in LLMs via Optimal Reasoning Trajectories Search](https://mlsanity.com/paper/2410.03864/) (2024)
- [Derailer-Rerailer: Adaptive Verification for Efficient and Reliable Language Model Reasoning](https://mlsanity.com/paper/2408.13940/) (2024)
- [Large Scale Question Answering using Tourism Data](https://mlsanity.com/paper/1909.03527/) (2019)

## Built on by (most cited first, 1 of 1)

- [Evaluating Agentic Learning Harness Capabilities Without Labels via the Scaling Hypothesis](https://mlsanity.com/paper/2608.13608/) (2026)

## Abstract (arXiv)

Evaluating large language models (LLMs) in specific domain like tourism remains challenging due to the prohibitive cost of annotated benchmarks and persistent issues like hallucinations. We propose Lable-Free Evaluation of LLM on Tourism using Expert Tree-of-Thought (LETToT), a framework that leverages expert-derived reasoning structures-instead of labeled data-to access LLMs in tourism. First, we iteratively refine and validate hierarchical ToT components through alignment with generic quality dimensions and expert feedback. Results demonstrate the effectiveness of our systematically optimized expert ToT with 4.99-14.15% relative quality gains over baselines. Second, we apply LETToT's optimized expert ToT to evaluate models of varying scales (32B-671B parameters), revealing: (1) Scaling laws persist in specialized domains (DeepSeek-V3 leads), yet reasoning-enhanced smaller models (e.g., DeepSeek-R1-Distill-Llama-70B) close this gap; (2) For sub-72B models, explicit reasoning architectures outperform counterparts in accuracy and conciseness (p<0.05). Our work established a scalable, label-free paradigm for domain-specific LLM evaluation, offering a robust alternative to conventional annotated benchmarks.