Traditional retrieval-augmented generation (RAG) benchmarks evaluate systems using heuristic-based metrics, but these require human preferences as the ground truth for reference. In contrast, arena-based benchmarks, where systems compete against each other, require an expensive large language model (LLM) as a judge for a reliable evaluation. We present a simple efficient technique to combine the best of both worlds. The idea is to train a surrogate judge using heuristic metrics as input, to output the LLM as a judge prediction.In our work, we develop MIRAGE-Bench, a synthetic arena-based RAG benchmark for 18 diverse languages on Wikipedia focused on multilingual answer generation evaluation. It extensively couples both heuristic features and LLM as a judge for evaluation. We benchmark 19 multilingual LLMs, and observe a high correlation (Kendall Tau (𝜏) = 0.909) using our surrogate judge and between GPT-4o as a teacher using the Bradley-Terry framework. Our results show proprietary and large open-source LLMs currently dominate on MIRAGE-Bench. Our code and datasets are made publicly available here: https://github.com/vectara/mirage-bench.

Summarization is one of the most common tasks performed by large language models (LLMs), especially in applications like Retrieval-Augmented Generation (RAG). However, existing evaluations of hallucinations in LLM-generated summaries, and evaluations of hallucination detection models both suffer from a lack of diversity and recency in the LLM and LLM families considered. This paper introduces FaithBench, a summarization hallucination benchmark comprising challenging hallucinations made by 10 modern LLMs from 8 different families, with ground truth annotations by human experts. “Challenging” here means summaries on which popular, state-of-the-art hallucination detection models, including GPT-4o-as-a-judge, disagreed on. Our results show GPT-4o and GPT-3.5-Turbo produce the least hallucinations. However, most state-of-the-art hallucination detection models have near 50% accuracies on FaithBench, indicating lots of room for future improvement.

Factual consistency detection has gotten raised attention in the task of abstractive summarization. Many existing works rely on synthetic training data, which may not accurately reflect or match the inconsistencies produced by summarization models. In this paper, we first systematically analyze the shortcomings of the current methods in synthesizing inconsistent summaries. Current synthesis methods may fail to produce inconsistencies of coreference errors and discourse errors, per our quantitative and qualitative study. Then, employing the parameter-efficient finetuning (PEFT) technique, we discover that a competitive factual consistency detector can be achieved using thousands of real model-generated summaries with human annotations. Our study demonstrates the importance of real machine-generated texts with human annotation in NLG evaluation as our model outperforms the SOTA on the CoGenSumm, FactCC, Frank, and SummEval datasets.

Summarization is an important application of Large Language Models (LLMs). When judging the quality of a summary, factual consistency holds a significant weight. Despite numerous efforts dedicated to building factual inconsistency detectors, the exploration of explanability remains limited among existing effort. In this study, we incorporate both human-annotated and model-generated natural language explanations elucidating how a summary deviates and thus becomes inconsistent with its source article. We build our explanation-augmented dataset on top of the widely used SummaC summarization consistency benchmark. Additionally, we develop an inconsistency detector that is jointly trained with the collected explanations. Our findings demonstrate that integrating explanations during training not only enables the model to provide rationales for its judgments but also enhances its accuracy significantly.

Automated summary quality assessment falls into two categories: reference-based and reference-free. Reference-based metrics, historically deemed more accurate due to the additional information provided by human-written references, are limited by their reliance on human input. In this paper, we hypothesize that the comparison methodologies used by some reference-based metrics to evaluate a system summary against its corresponding reference can be effectively adapted to assess it against its source document, thereby transforming these metrics into reference-free ones. Experimental results support this hypothesis. After being repurposed reference-freely, the zero-shot BERTScore using the pretrained DeBERTa-large-MNLI model of <0.5B parameters consistently outperforms its original reference-based version across various aspects on the SummEval and Newsroom datasets. It also excels in comparison to most existing reference-free metrics and closely competes with zero-shot summary evaluators based on GPT-3.5.

Evaluating machine-generated summaries without a human-written reference summary has been a need for a long time. Inspired by preference labeling in existing work of summarization evaluation, we propose to judge summary quality by learning the preference rank of summaries using the Bradley-Terry power ranking model from inferior summaries generated by corrupting base summaries. Extensive experiments on several datasets show that our weakly supervised scheme can produce scores highly correlated with human ratings.

Canonical automatic summary evaluation metrics, such as ROUGE, focus on lexical similarity which cannot well capture semantics nor linguistic quality and require a reference summary which is costly to obtain. Recently, there have been a growing number of efforts to alleviate either or both of the two drawbacks. In this paper, we present a proof-of-concept study to a weakly supervised summary evaluation approach without the presence of reference summaries. Massive data in existing summarization datasets are transformed for training by pairing documents with corrupted reference summaries. In cross-domain tests, our strategy outperforms baselines with promising improvements, and show a great advantage in gauging linguistic qualities over all metrics.