Existing large language models (LLMs) occasionally generate plausible yet factually incorrect responses, known as hallucinations. Two main approaches have been proposed to mitigate hallucinations: retrieval-augmented language models (RALMs) and refusal post-training. However, current research predominantly focuses on their individual effectiveness while overlooking the evaluation of the refusal capability of RALMs. Ideally, if RALMs know when they do not know, they should refuse to answer.In this study, we ask the fundamental question: Do RALMs know when they don't know? Specifically, we investigate three questions. First, are RALMs well calibrated with respect to different internal and external knowledge states? We examine the influence of various factors. Contrary to expectations, when all retrieved documents are irrelevant, RALMs still tend to refuse questions they could have answered correctly. Next, given the model's pronounced \textbf{over-refusal} behavior, we raise a second question: How does a RALM's refusal ability align with its calibration quality? Our results show that the over-refusal problem can be mitigated through in-context fine-tuning. However, we observe that improved refusal behavior does not necessarily imply better calibration or higher overall accuracy. Finally, we ask: Can we combine refusal-aware RALMs with uncertainty-based answer abstention to mitigate over-refusal? We develop a simple yet effective refusal mechanism for refusal-post-trained RALMs that improves their overall answer quality by balancing refusal and correct answers. Our study provides a more comprehensive understanding of the factors influencing RALM behavior. Meanwhile, we emphasize that uncertainty estimation for RALMs remains an open problem deserving deeper investigation.

Abstract--Retrieval-Augmented Generation (RAG) is an effective method to enhance the capabilities of large language models (LLMs). Existing methods typically optimize the retriever or the generator in a RAG system by directly using the top-k retrieved documents. However, two key issues inherent in the training data constrain the effectiveness of this training paradigm: (1) across different queries, the top-k retrieved documents vary greatly in content quality, with some providing valuable knowledge while others lack critical information or are even misleading, and training on such data in a purely random manner may impair the generator's ability to extract key information; (2) for a given query, the limited set of k documents often exhibits low discriminability, and training solely on them makes it difficult for the retriever to learn how to distinguish between relevant and irrelevant documents. T o address these issues, we introduce DACL-RAG, a multi-stage RAG training framework that combines a multi-level Data Augmentation strategy with a multistage Curriculum Learning paradigm. The data augmentation strategy constructs comprehensive and diverse training sets with controllable difficulty levels through sample evolution, while the curriculum learning paradigm organizes them into progressive stages for training, ensuring stable and consistent improvements, thereby optimizing the overall performance and generalization of the RAG system more effectively. Our DACL-RAG framework demonstrates consistent effectiveness across four open-domain QA datasets, achieving performance gains of 2% to 4% over multiple advanced methods. ARGE language models (LLMs) have demonstrated remarkable capabilities in a wide range of Natural Language Processing (NLP) tasks [1]-[3], but they are still constrained by the limitations of the static knowledge embedded within their internal parameters [4]-[6]. Retrieval-Augmented Generation (RAG) addresses this limitation by supplementing LLMs with additional knowledge retrieved from external knowledge bases, and has significantly enhanced the capabilities of existing large models in tasks such as Open-Domain Question Answering [7]-[17] and Dialog System [18]-[20]. The overall performance of the RAG system depends crucially on the quality of the retrieved documents and the LLMs' ability to effectively utilize them. Shaohan Wang, Licheng Zhang and Zheren Fu are with the School of Information Science and Technology, University of Science and Technology of China, Hefei, Anhui 230022, China (e-mail: wsh2000@mail.ustc.edu.cn; Zhendong Mao and Y ongdong Zhang are with the School of Information Science and Technology, University of Science and Technology of China, and the Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, Anhui 230022, China (e-mail: zhyd73@ustc.edu.cn; Here, green denotes documents that support the model's responses, while red denotes documents that are useless or even harmful.

Large Language Models (LLMs) have demonstrated remarkable capabilities in natural language understanding and generation tasks, revolutionizing how machines interact with human language. Despite their impressive performance, these models continue to struggle with factual accuracy, often producing content that appears plausible but contains incorrect information--a phenomenon commonly referred to as "hallucination"[1]. However, despite their conceptual elegance, RALMs face several critical challenges that undermine their effectiveness in real-world scenarios. First, these systems often struggle to distinguish between relevant and irrelevant retrieved documents, treating all retrievals with equal importance regardless of their actual utility for answering the query at hand. Second, standard RALMs frequently over-rely on external retrievals even in situations where their intrinsic knowledge would be sufficient or more reliable. This rigid dependence on external sources fails to leverage the substantial knowledge already encoded in model parameters during pre-training and fine-tuning. Perhaps most concerning is RALMs' inability to acknowledge knowledge gaps when confronted with queries that cannot be answered based on either retrieved information or intrinsic knowledge. Instead of transparently communicating limitations--a crucial capability for trustworthy AI systems--these models often generate fabricated responses that appear authoritative despite lacking factual foundation.

Retrieval-Augmented Language Models boost task performance, owing to the retriever that provides external knowledge. Although crucial, the retriever primarily focuses on semantics relevance, which may not always be effective for generation. Thus, utility-based retrieval has emerged as a promising topic, prioritizing passages that provides valid benefits for downstream tasks. However, due to insufficient understanding, capturing passage utility accurately remains unexplored. This work proposes SCARLet, a framework for training utility-based retrievers in RALMs, which incorporates two key factors, multi-task generalization and inter-passage interaction. First, SCARLet constructs shared context on which training data for various tasks is synthesized. This mitigates semantic bias from context differences, allowing retrievers to focus on learning task-specific utility for better task generalization. Next, SCARLet uses a perturbation-based attribution method to estimate passage-level utility for shared context, which reflects interactions between passages and provides more accurate feedback. We evaluate our approach on ten datasets across various tasks, both in-domain and out-of-domain, showing that retrievers trained by SCARLet consistently improve the overall performance of RALMs.

Despite the significant progress made by existing retrieval augmented language models (RALMs) in providing trustworthy responses and grounding in reliable sources, they often overlook effective alignment with human preferences. In the alignment process, reward models (RMs) act as a crucial proxy for human values to guide optimization. However, it remains unclear how to evaluate and select a reliable RM for preference alignment in RALMs. To this end, we propose RAG-RewardBench, the first benchmark for evaluating RMs in RAG settings. First, we design four crucial and challenging RAG-specific scenarios to assess RMs, including multi-hop reasoning, fine-grained citation, appropriate abstain, and conflict robustness. Then, we incorporate 18 RAG subsets, six retrievers, and 24 RALMs to increase the diversity of data sources. Finally, we adopt an LLM-as-a-judge approach to improve preference annotation efficiency and effectiveness, exhibiting a strong correlation with human annotations. Based on the RAG-RewardBench, we conduct a comprehensive evaluation of 45 RMs and uncover their limitations in RAG scenarios. Additionally, we also reveal that existing trained RALMs show almost no improvement in preference alignment, highlighting the need for a shift towards preference-aligned training.We release our benchmark and code publicly at https://huggingface.co/datasets/jinzhuoran/RAG-RewardBench/ for future work.

RALMs (Retrieval-Augmented Language Models) broaden their knowledge scope by incorporating external textual resources. However, the multilingual nature of global knowledge necessitates RALMs to handle diverse languages, a topic that has received limited research focus. In this work, we propose \textit{Futurepedia}, a carefully crafted benchmark containing parallel texts across eight representative languages. We evaluate six multilingual RALMs using our benchmark to explore the challenges of multilingual RALMs. Experimental results reveal linguistic inequalities: 1) high-resource languages stand out in Monolingual Knowledge Extraction; 2) Indo-European languages lead RALMs to provide answers directly from documents, alleviating the challenge of expressing answers across languages; 3) English benefits from RALMs' selection bias and speaks louder in multilingual knowledge selection. Based on these findings, we offer advice for improving multilingual Retrieval Augmented Generation. For monolingual knowledge extraction, careful attention must be paid to cascading errors from translating low-resource languages into high-resource ones. In cross-lingual knowledge transfer, encouraging RALMs to provide answers within documents in different languages can improve transfer performance. For multilingual knowledge selection, incorporating more non-English documents and repositioning English documents can help mitigate RALMs' selection bias. Through comprehensive experiments, we underscore the complexities inherent in multilingual RALMs and offer valuable insights for future research.

Retrieval Augmented Language Models (RALMs) have gained significant attention for their ability to generate accurate answer and improve efficiency. However, RALMs are inherently vulnerable to imperfect information due to their reliance on the imperfect retriever or knowledge source. We identify three common scenarios-unanswerable, adversarial, conflicting-where retrieved document sets can confuse RALM with plausible real-world examples. We present the first comprehensive investigation to assess how well RALMs detect and handle such problematic scenarios. Among these scenarios, to systematically examine adversarial robustness we propose a new adversarial attack method, Generative model-based ADVersarial attack (GenADV) and a novel metric Robustness under Additional Document (RAD). Our findings reveal that RALMs often fail to identify the unanswerability or contradiction of a document set, which frequently leads to hallucinations. Moreover, we show the addition of an adversary significantly degrades RALM's performance, with the model becoming even more vulnerable when the two scenarios overlap (adversarial+unanswerable). Our research identifies critical areas for assessing and enhancing the robustness of RALMs, laying the foundation for the development of more robust models.

Retrieval-Augmented Large Language Models (RALMs) have made significant strides in enhancing the accuracy of generated responses.However, existing research often overlooks the data quality issues within retrieval results, often caused by inaccurate existing vector-distance-based retrieval methods.We propose to boost the precision of RALMs' answers from a data quality perspective through the Context-Driven Index Trimming (CDIT) framework, where Context Matching Dependencies (CMDs) are employed as logical data quality rules to capture and regulate the consistency between retrieved contexts.Based on the semantic comprehension capabilities of Large Language Models (LLMs), CDIT can effectively identify and discard retrieval results that are inconsistent with the query context and further modify indexes in the database, thereby improving answer quality.Experiments demonstrate on challenging question-answering tasks.Also, the flexibility of CDIT is verified through its compatibility with various language models and indexing methods, which offers a promising approach to bolster RALMs' data quality and retrieval precision jointly.

Retrieval-Augmented Language Models (RALMs) have significantly improved performance in open-domain question answering (QA) by leveraging external knowledge. However, RALMs still struggle with unanswerable queries, where the retrieved contexts do not contain the correct answer, and with conflicting information, where different sources provide contradictory answers due to imperfect retrieval. This study introduces an in-context learning-based approach to enhance the reasoning capabilities of RALMs, making them more robust in imperfect retrieval scenarios. Our method incorporates Machine Reading Comprehension (MRC) demonstrations, referred to as cases, to boost the model's capabilities to identify unanswerabilities and conflicts among the retrieved contexts. Experiments on two open-domain QA datasets show that our approach increases accuracy in identifying unanswerable and conflicting scenarios without requiring additional fine-tuning. This work demonstrates that in-context learning can Figure 1: Examples of unanswerable and conflict scenario effectively enhance the robustness of RALMs that may arise during retrieval-augmenation.

The Retrieval-Augmented Language Model (RALM) has shown remarkable performance on knowledge-intensive tasks by incorporating external knowledge during inference, which mitigates the factual hallucinations inherited in large language models (LLMs). Despite these advancements, challenges persist in the implementation of RALMs, particularly concerning their reliability and traceability. To be specific, the irrelevant document retrieval may result in unhelpful response generation or even deteriorate the performance of LLMs, while the lack of proper citations in generated outputs complicates efforts to verify the trustworthiness of the models. To this end, we propose a novel self-reasoning framework aimed at improving the reliability and traceability of RALMs, whose core idea is to leverage reasoning trajectories generated by the LLM itself. The framework involves constructing self-reason trajectories with three processes: a relevance-aware process, an evidence-aware selective process, and a trajectory analysis process. We have evaluated our framework across four public datasets (two short-form QA datasets, one long-form QA dataset, and one fact verification dataset) to demonstrate the superiority of our method, which can outperform existing state-of-art models and can achieve comparable performance with GPT-4, while only using 2,000 training samples.