# TRACE: Tourism Recommendation with Accountable Citation Evidence

arXiv: https://arxiv.org/abs/2605.07677 · HTML: https://mlsanity.com/paper/2605.07677/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 46 of its 60 references that are in the map.
- First posted on arXiv 8 May 2026.

## Builds on (most cited first, 30 of 46)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Datasheets for Datasets](https://mlsanity.com/paper/1803.09010/) (2018)
- [DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines](https://mlsanity.com/paper/2310.03714/) (2023)
- [Enabling Large Language Models to Generate Text with Citations](https://mlsanity.com/paper/2305.14627/) (2023)
- [ASQA: Factoid Questions Meet Long-Form Answers](https://mlsanity.com/paper/2204.06092/) (2022)
- [Towards Deep Conversational Recommendations](https://mlsanity.com/paper/1812.07617/) (2018)
- [A Survey on Conversational Recommender Systems](https://mlsanity.com/paper/2004.00646/) (2020)
- [FaithDial: A Faithful Benchmark for Information-Seeking Dialogue](https://mlsanity.com/paper/2204.10757/) (2022)
- [Towards Conversational Recommendation over Multi-Type Dialogs](https://mlsanity.com/paper/2005.03954/) (2020)
- [Towards Topic-Guided Conversational Recommender System](https://mlsanity.com/paper/2010.04125/) (2020)
- [INSPIRED: Toward Sociable Recommendation Dialog Systems](https://mlsanity.com/paper/2009.14306/) (2020)
- [Towards Unified Conversational Recommender Systems via Knowledge-Enhanced Prompt Learning](https://mlsanity.com/paper/2206.09363/) (2022)
- [Joint Deep Modeling of Users and Items Using Reviews for Recommendation](https://mlsanity.com/paper/1701.04783/) (2017)
- [A Review of Modern Recommender Systems Using Generative Models (Gen-RecSys)](https://mlsanity.com/paper/2404.00579/) (2024)
- [The FACTS Grounding Leaderboard: Benchmarking LLMs' Ability to Ground Responses to Long-Form Input](https://mlsanity.com/paper/2501.03200/) (2025)
- [DuRecDial 2.0: A Bilingual Parallel Corpus for Conversational Recommendation](https://mlsanity.com/paper/2109.08877/) (2021)
- [ITINERA: Integrating Spatial Optimization with Large Language Models for Open-domain Urban Itinerary Planning](https://mlsanity.com/paper/2402.07204/) (2024)
- [Improving Conversational Recommendation Systems' Quality with Context-Aware Item Meta Information](https://mlsanity.com/paper/2112.08140/) (2021)
- [Citation: A Key to Building Responsible and Accountable Large Language Models](https://mlsanity.com/paper/2307.02185/) (2023)
- [Retrieval-Augmented Conversational Recommendation with Prompt-based Semi-Structured Natural Language State Tracking](https://mlsanity.com/paper/2406.00033/) (2024)
- [Pearl: A Review-driven Persona-Knowledge Grounded Conversational Recommendation Dataset](https://mlsanity.com/paper/2403.04460/) (2024)
- [TRACE the Evidence: Constructing Knowledge-Grounded Reasoning Chains for Retrieval-Augmented Generation](https://mlsanity.com/paper/2406.11460/) (2024)
- [TREA: Tree-Structure Reasoning Schema for Conversational Recommendation](https://mlsanity.com/paper/2307.10543/) (2023)
- [ReasoningRec: Bridging Personalized Recommendations and Human-Interpretable Explanations through LLM Reasoning](https://mlsanity.com/paper/2410.23180/) (2024)
- [Spatial-RAG: Spatial Retrieval Augmented Generation for Real-World Geospatial Reasoning Questions](https://mlsanity.com/paper/2502.18470/) (2025)
- [TP-RAG: Benchmarking Retrieval-Augmented Large Language Model Agents for Spatiotemporal-Aware Travel Planning](https://mlsanity.com/paper/2504.08694/) (2025)
- [RETAIL: Towards Real-world Travel Planning for Large Language Models](https://mlsanity.com/paper/2508.15335/) (2025)
- [Explicit Knowledge Graph Reasoning for Conversational Recommendation](https://mlsanity.com/paper/2305.00783/) (2023)
- [SynthTRIPs: A Knowledge-Grounded Framework for Benchmark Query Generation for Personalized Tourism Recommenders](https://mlsanity.com/paper/2504.09277/) (2025)
- [Fin-RATE: A Real-world Financial Analytics and Tracking Evaluation Benchmark for LLMs on SEC Filings](https://mlsanity.com/paper/2602.07294/) (2026)

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

- [Replan, Repair, or Edit? A Unified Empirical Evaluation of Travel Agents for Itinerary Revision under Resource Disruptions](https://mlsanity.com/paper/2609.19654/) (2026)

## Abstract (arXiv)

Tourism is a high-stakes setting for conversational recommender systems (CRS): a plausible-sounding suggestion can waste real money and trip time once a traveler acts on it. Existing CRS benchmarks primarily evaluate systems with a single Recall@k score over entity mentions, and tourism-specific resources add spatial or knowledge-graph context, yet none of them couple multi-turn recommendation with verbatim review-span evidence and rejection recovery. This leaves an evaluation gap for tourism recommendation that is simultaneously trustworthy, verifiable, and adaptive: recommend the right point of interest (POI) for multi-aspect preferences (such as cuisine, price, atmosphere, walking distance), justify each suggestion with verifiable evidence from prior visitors so the traveler can act without trial and error, and recover when the first recommendation is rejected mid-dialogue. We introduce TRACE, where each item is a multi-turn tourism recommendation dialogue with review-span citations and explicit rejection turns: 10,000 dialogues over 2,400 Yelp POIs and 34,208 reviews across eight U.S. cities, paired with 14 retrieval, planning, and LLM baselines, along with 25 metrics organized under Accuracy, Grounding, and Recovery. Across these baselines, TRACE reveals the Three-Competency Gap: LLM Zero-Shot leads in closed-set Recall@1 and rejection recovery but cites less densely than retrievers; non-LLM retrievers achieve surface-verbatim grounding but with low accuracy; Multi-Review Synthesis fails at recovery. The Grounding Score agrees with human citation precision (Spearman rho=+0.80, p<10^-20), and paired t-tests reproduce the per-baseline ranking (p<0.01 on the dominant contrasts). TRACE reframes accountable tourism recommendation as a joint target (right POI, verifiable evidence, adaptive repair) rather than a single-axis leaderboard.