# Faithfulness metric fusion: Improving the evaluation of LLM trustworthiness across domains

arXiv: https://arxiv.org/abs/2512.05700 · HTML: https://mlsanity.com/paper/2512.05700/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 40 references that are in the map.
- First posted on arXiv 5 Dec 2025.

## Builds on (most cited first, 29 of 29)

- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation](https://mlsanity.com/paper/2305.14251/) (2023)
- [When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories](https://mlsanity.com/paper/2212.10511/) (2022)
- [SummEval: Re-evaluating Summarization Evaluation](https://mlsanity.com/paper/2007.12626/) (2020)
- [Evaluating the Factual Consistency of Abstractive Text Summarization](https://mlsanity.com/paper/1910.12840/) (2019)
- [SAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive Summarization](https://mlsanity.com/paper/1911.12237/) (2019)
- [Towards Scalable Multi-domain Conversational Agents: The Schema-Guided Dialogue Dataset](https://mlsanity.com/paper/1909.05855/) (2019)
- [Asking and Answering Questions to Evaluate the Factual Consistency of Summaries](https://mlsanity.com/paper/2004.04228/) (2020)
- [Humans or LLMs as the Judge? A Study on Judgement Biases](https://mlsanity.com/paper/2402.10669/) (2024)
- [InterpretML: A Unified Framework for Machine Learning Interpretability](https://mlsanity.com/paper/1909.09223/) (2019)
- [MultiWOZ 2.2 : A Dialogue Dataset with Additional Annotation Corrections and State Tracking Baselines](https://mlsanity.com/paper/2007.12720/) (2020)
- [To Ship or Not to Ship: An Extensive Evaluation of Automatic Metrics for Machine Translation](https://mlsanity.com/paper/2107.10821/) (2021)
- [Evaluating Correctness and Faithfulness of Instruction-Following Models for Question Answering](https://mlsanity.com/paper/2307.16877/) (2023)
- [Assessing The Factual Accuracy of Generated Text](https://mlsanity.com/paper/1905.13322/) (2019)
- [The Dawn After the Dark: An Empirical Study on Factuality Hallucination in Large Language Models](https://mlsanity.com/paper/2401.03205/) (2024)
- [SpokenWOZ: A Large-Scale Speech-Text Benchmark for Spoken Task-Oriented Dialogue Agents](https://mlsanity.com/paper/2305.13040/) (2023)
- [FABLES: Evaluating faithfulness and content selection in book-length summarization](https://mlsanity.com/paper/2404.01261/) (2024)
- [AMR Parsing as Sequence-to-Graph Transduction](https://mlsanity.com/paper/1905.08704/) (2019)
- [FactGraph: Evaluating Factuality in Summarization with Semantic Graph Representations](https://mlsanity.com/paper/2204.06508/) (2022)
- [Evaluating Open-QA Evaluation](https://mlsanity.com/paper/2305.12421/) (2023)
- [Towards LLM-driven Dialogue State Tracking](https://mlsanity.com/paper/2310.14970/) (2023)
- [Are Large Language Models Reliable Judges? A Study on the Factuality Evaluation Capabilities of LLMs](https://mlsanity.com/paper/2311.00681/) (2023)
- [QAConv: Question Answering on Informative Conversations](https://mlsanity.com/paper/2105.06912/) (2021)
- [Towards Fair Evaluation of Dialogue State Tracking by Flexible Incorporation of Turn-level Performances](https://mlsanity.com/paper/2204.03375/) (2022)
- [Predictions from language models for multiple-choice tasks are not robust under variation of scoring methods](https://mlsanity.com/paper/2403.00998/) (2024)
- [Accurate and Nuanced Open-QA Evaluation Through Textual Entailment](https://mlsanity.com/paper/2405.16702/) (2024)
- [Evaluating the Retrieval Component in LLM-Based Question Answering Systems](https://mlsanity.com/paper/2406.06458/) (2024)
- [STORYSUMM: Evaluating Faithfulness in Story Summarization](https://mlsanity.com/paper/2407.06501/) (2024)
- [A review of faithfulness metrics for hallucination assessment in Large Language Models](https://mlsanity.com/paper/2501.00269/) (2024)

## Abstract (arXiv)

We present a methodology for improving the accuracy of faithfulness evaluation in Large Language Models (LLMs). The proposed methodology is based on the combination of elementary faithfulness metrics into a combined (fused) metric, for the purpose of improving the faithfulness of LLM outputs. The proposed strategy for metric fusion deploys a tree-based model to identify the importance of each metric, which is driven by the integration of human judgements evaluating the faithfulness of LLM responses. This fused metric is demonstrated to correlate more strongly with human judgements across all tested domains for faithfulness. Improving the ability to evaluate the faithfulness of LLMs, allows for greater confidence to be placed within models, allowing for their implementation in a greater diversity of scenarios. Additionally, we homogenise a collection of datasets across question answering and dialogue-based domains and implement human judgements and LLM responses within this dataset, allowing for the reproduction and trialling of faithfulness evaluation across domains.