mlsanityData to 14 Oct 2026

TRACE: Trustworthy Retrieval-Augmented Conversational Engine

arXiv 2608.10176 ↗First posted 10 Aug 2026cs.AIcited by 0

On the map: Retrieval-augmented generation → RAG robustness and adaptive retrieval

Abstract (arXiv)

Public service chatbots are expected to deliver recommendations from an underlying public service directory, while also making sure that the recommendations respect explicit user constraints. In practice, public service directories are noisy and inconsistent, and general-purpose large language model (LLM) or AI-based chatbots frequently generate unreliable recommendations, citing unverified sources from the web. We investigate the impact of retrieval quality on constraint-aware recommendation in public service conversational systems built over noisy and heterogeneous service directories. We propose TRACE (Trustworthy Retrieval-Augmented Conversational Engine), a retrieval-based, constraint-aware framework that parses input user queries into structural and semantic constraints for downstream retrieval, with the help of a dual data representation schema. Using a curated statewide pantry directory and a synthetic query benchmark, we evaluate multiple knowledge-representation variants with and without knowledge graphs (KGs). We experiment with several open-source LLMs and a proprietary model, showing that strengthening retrieval substantially improves user constraint satisfaction while reducing hallucinated recommendations. Performance differences across LLMs narrowed in our experiments as retrieval quality improved, making results less sensitive to model size. These findings suggest that the quality of retrieval is key for robust public service conversational systems.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RAG robustness and adaptive retrieval, one of 15 directions in Retrieval-augmented generation. Builds on 11 of its 37 references that are in the map. First posted on arXiv 10 Aug 2026.

Builds on

11 of 37 references.

References · 11

  1. 2025Qwen3 Technical Reportcited by 8,820
  2. 2020doc2dial: A Goal-Oriented Document-Grounded Dialogue Datasetcited by 88
  3. 2024Simple Is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generationcited by 80
  4. 2025Knowledge Graph-Guided Retrieval Augmented Generationcited by 58
  5. 2021MultiDoc2Dial: Modeling Dialogues Grounded in Multiple Documentscited by 53
  6. 2020Recent Neural Methods on Slot Filling and Intent Classification for Task-Oriented Dialogue Systems: A Surveycited by 51
  7. 2021Ask what's missing and what's useful: Improving Clarification Question Generation using Global Knowledgecited by 40
  8. 2025The Confidence Paradox: Can LLM Know When It's Wrongcited by 11
  9. 2025Can Knowledge-Graph-based Retrieval Augmented Generation Really Retrieve What You Need?cited by 8
  10. 2025Hybrid Graphs for Table-and-Text based Question Answering using LLMscited by 7
  11. 2026Retrieval Challenges in Low-Resource Public Service Information: A Case Study on Food Pantry Accesscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025A Knowledge Graph and a Tripartite Evaluation Framework Make Retrieval-Augmented Generation Scalable and Transparent
  2. 2024Evaluating the Retrieval Component in LLM-Based Question Answering Systems
  3. 2024Trustworthiness in Retrieval-Augmented Generation Systems: A Survey
  4. 2025ReGeS: Reciprocal Retrieval-Generation Synergy for Conversational Recommender Systems
  5. 2025Retrieval-augmented reasoning with lean language models
  6. 2026MTR-Suite: A Framework for Evaluating and Synthesizing Conversational Retrieval Benchmarks
  7. 2026τ-Knowledge: Evaluating Conversational Agents over Unstructured Knowledge
  8. 2026AWARE-US: Preference-Aware Infeasibility Resolution in Tool-Calling Agents