Retrieval-augmented generation (RAG) can significantly improve the performance of language models (LMs) by providing additional context for tasks such as document-based question answering (DBQA). However, the effectiveness of RAG is highly dependent on its configuration. To systematically find the optimal configuration, we introduce RAGGED, a framework for analyzing RAG configurations across various DBQA tasks. Using the framework, we discover distinct LM behaviors in response to varying context quantities, context qualities, and retrievers. For instance, while some models are robust to noisy contexts, monotonically performing better with more contexts, others are more noise-sensitive and can effectively use only a few contexts before declining in performance. This framework also provides a deeper analysis of these differences by evaluating the LMs' sensitivity to signal and noise under specific context quality conditions. Using RAGGED, researchers and practitioners can derive actionable insights about how to optimally configure their RAG systems for their specific question-answering tasks.
We explore a strategy to handle controversial topics in LLM-based chatbots based on Wikipedia's Neutral Point of View (NPOV) principle: acknowledge the absence of a single true answer and surface multiple perspectives. We frame this as retrieval augmented generation, where perspectives are retrieved from a knowledge base and the LLM is tasked with generating a fluent and faithful response from the given perspectives. As a starting point, we use a deterministic retrieval system and then focus on common LLM failure modes that arise during this approach to text generation, namely hallucination and coverage errors. We propose and evaluate three methods to detect such errors based on (1) word-overlap, (2) salience, and (3) LLM-based classifiers. Our results demonstrate that LLM-based classifiers, even when trained only on synthetic errors, achieve high error detection performance, with ROC AUC scores of 95.3% for hallucination and 90.5% for coverage error detection on unambiguous error cases. We show that when no training data is available, our other methods still yield good results on hallucination (84.0%) and coverage error (85.2%) detection.
The conventional process of building Ontologies and Knowledge Graphs (KGs) heavily relies on human domain experts to define entities and relationship types, establish hierarchies, maintain relevance to the domain, fill the ABox (or populate with instances), and ensure data quality (including amongst others accuracy and completeness). On the other hand, Large Language Models (LLMs) have recently gained popularity for their ability to understand and generate human-like natural language, offering promising ways to automate aspects of this process. This work explores the (semi-)automatic construction of KGs facilitated by open-source LLMs. Our pipeline involves formulating competency questions (CQs), developing an ontology (TBox) based on these CQs, constructing KGs using the developed ontology, and evaluating the resultant KG with minimal to no involvement of human experts. We showcase the feasibility of our semi-automated pipeline by creating a KG on deep learning methodologies by exploiting scholarly publications. To evaluate the answers generated via Retrieval-Augmented-Generation (RAG) as well as the KG concepts automatically extracted using LLMs, we design a judge LLM, which rates the generated content based on ground truth. Our findings suggest that employing LLMs could potentially reduce the human effort involved in the construction of KGs, although a human-in-the-loop approach is recommended to evaluate automatically generated KGs.
Retrieval-augmented generation (RAG) can enhance the generation quality of large language models (LLMs) by incorporating external token databases. However, retrievals from large databases can constitute a substantial portion of the overall generation time, particularly when retrievals are periodically performed to align the retrieved content with the latest states of generation. In this paper, we introduce PipeRAG, a novel algorithm-system co-design approach to reduce generation latency and enhance generation quality. PipeRAG integrates (1) pipeline parallelism to enable concurrent retrieval and generation processes, (2) flexible retrieval intervals to maximize the efficiency of pipeline parallelism, and (3) a performance model to automatically balance retrieval quality and latency based on the generation states and underlying hardware. Our evaluation shows that, by combining the three aforementioned methods, PipeRAG achieves up to 2.6$\times$ speedup in end-to-end generation latency while improving generation quality. These promising results showcase the effectiveness of co-designing algorithms with underlying systems, paving the way for the adoption of PipeRAG in future RAG systems.
Unlike professional caregivers, family caregivers often assume this role without formal preparation or training. Because of this, there is an urgent need to enhance the capacity of family caregivers to provide quality care. Large language models can potentially be used as a foundation technology for supporting caregivers as educational tools or as adjunct to care. This study aimed to develop a reliable Caregiving Language Model (CaLM) by using FMs and a caregiving knowledge base, develop an accessible CaLM using a small FM that requires fewer computing resources, and evaluate the performance of the model compared to a large FM. We developed CaLM using the Retrieval Augmented Generation (RAG) framework combined with FM fine-tuning for improving the quality of FM answers by grounding the model on a caregiving knowledge base. We used two small FMs as candidates for the FM of CaLM (LLaMA-2 and Falcon with 7B parameters) and larger FM GPT-3.5 as a benchmark. We developed the caregiving knowledge base by gathering various types of documents from the Internet. In this study, we focused on caregivers of individuals with Alzheimer's Disease Related Dementias. We evaluated the models' performance using the benchmark metrics commonly used in evaluating language models and their reliability to provide accurate references with the answers. The RAG framework improved the performance of all FMs used in this study across all measures. As expected, the large FM performed better than small FMs across all metrics. The most interesting result is that small fine-tuned FMs with RAG performed significantly better than GPT 3.5 across all metrics. The fine-tuned LLaMA-2 small FM performed better than GPT 3.5 (even with RAG) in returning references with the answers. The study shows that reliable and accessible CaLM can be developed by using small FMs with a knowledge base specific to the caregiving domain.
Large language models (LLMs) demonstrate exceptional performance in numerous tasks but still heavily rely on knowledge stored in their parameters. Moreover, updating this knowledge incurs high training costs. Retrieval-augmented generation (RAG) methods address this issue by integrating external knowledge. The model can answer questions it couldn't previously by retrieving knowledge relevant to the query. This approach improves performance in certain scenarios for specific tasks. However, if irrelevant texts are retrieved, it may impair model performance. In this paper, we propose Retrieval Augmented Iterative Self-Feedback (RA-ISF), a framework that iteratively decomposes tasks and processes them in three submodules to enhance the model's problem-solving capabilities. Experiments show that our method outperforms existing benchmarks, performing well on models like GPT3.5, Llama2, significantly enhancing factual reasoning capabilities and reducing hallucinations.
Hallucinations pose a significant challenge to the reliability of large language models (LLMs) in critical domains. Recent benchmarks designed to assess LLM hallucinations within conventional NLP tasks, such as knowledge-intensive question answering (QA) and summarization, are insufficient for capturing the complexities of user-LLM interactions in dynamic, real-world settings. To address this gap, we introduce HaluEval-Wild, the first benchmark specifically designed to evaluate LLM hallucinations in the wild. We meticulously collect challenging (adversarially filtered by Alpaca) user queries from ShareGPT, an existing real-world user-LLM interaction datasets, to evaluate the hallucination rates of various LLMs. Upon analyzing the collected queries, we categorize them into five distinct types, which enables a fine-grained analysis of the types of hallucinations LLMs exhibit, and synthesize the reference answers with the powerful GPT-4 model and retrieval-augmented generation (RAG). Our benchmark offers a novel approach towards enhancing our comprehension of and improving LLM reliability in scenarios reflective of real-world interactions. Our benchmark is available at https://github.com/HaluEval-Wild/HaluEval-Wild.
The increasing interest in Large Language Models (LLMs) within the telecommunications sector underscores their potential to revolutionize operational efficiency. However, the deployment of these sophisticated models is often hampered by their substantial size and computational demands, raising concerns about their viability in resource-constrained environments. Addressing this challenge, recent advancements have seen the emergence of small language models that surprisingly exhibit performance comparable to their larger counterparts in many tasks, such as coding and common-sense reasoning. Phi-2, a compact yet powerful model, exemplifies this new wave of efficient small language models. This paper conducts a comprehensive evaluation of Phi-2's intrinsic understanding of the telecommunications domain. Recognizing the scale-related limitations, we enhance Phi-2's capabilities through a Retrieval-Augmented Generation approach, meticulously integrating an extensive knowledge base specifically curated with telecom standard specifications. The enhanced Phi-2 model demonstrates a profound improvement in accuracy, answering questions about telecom standards with a precision that closely rivals the more resource-intensive GPT-3.5. The paper further explores the refined capabilities of Phi-2 in addressing problem-solving scenarios within the telecom sector, highlighting its potential and limitations.
Federated Recommendation (FR) emerges as a novel paradigm that enables privacy-preserving recommendations. However, traditional FR systems usually represent users/items with discrete identities (IDs), suffering from performance degradation due to the data sparsity and heterogeneity in FR. On the other hand, Large Language Models (LLMs) as recommenders have proven effective across various recommendation scenarios. Yet, LLM-based recommenders encounter challenges such as low inference efficiency and potential hallucination, compromising their performance in real-world scenarios. To this end, we propose GPT-FedRec, a federated recommendation framework leveraging ChatGPT and a novel hybrid Retrieval Augmented Generation (RAG) mechanism. GPT-FedRec is a two-stage solution. The first stage is a hybrid retrieval process, mining ID-based user patterns and text-based item features. Next, the retrieved results are converted into text prompts and fed into GPT for re-ranking. Our proposed hybrid retrieval mechanism and LLM-based re-rank aims to extract generalized features from data and exploit pretrained knowledge within LLM, overcoming data sparsity and heterogeneity in FR. In addition, the RAG approach also prevents LLM hallucination, improving the recommendation performance for real-world users. Experimental results on diverse benchmark datasets demonstrate the superior performance of GPT-FedRec against state-of-the-art baseline methods.
The demand for accurate and efficient verification of information in texts generated by large language models (LMs) is at an all-time high, but remains unresolved. Recent efforts have focused on extracting and verifying atomic facts from these texts via prompting LM evaluators. However, we demonstrate that this method of prompting is unreliable when faced with incomplete or inaccurate reference information. We introduce Facts as a Function (FaaF), a new approach to the fact verification task that leverages the function-calling capabilities of LMs. FaaF significantly enhances the ability of LMs to identify unsupported facts in texts, while also improving efficiency and significantly lowering costs compared to prompt-based methods. Additionally, we propose a framework for evaluating factual recall in Retrieval Augmented Generation (RAG) systems, which we employ to compare prompt-based and FaaF methods using various LMs under challenging conditions.
We introduce a new family of prompt injection attacks, termed Neural Exec. Unlike known attacks that rely on handcrafted strings (e.g., "Ignore previous instructions and..."), we show that it is possible to conceptualize the creation of execution triggers as a differentiable search problem and use learning-based methods to autonomously generate them. Our results demonstrate that a motivated adversary can forge triggers that are not only drastically more effective than current handcrafted ones but also exhibit inherent flexibility in shape, properties, and functionality. In this direction, we show that an attacker can design and generate Neural Execs capable of persisting through multi-stage preprocessing pipelines, such as in the case of Retrieval-Augmented Generation (RAG)-based applications. More critically, our findings show that attackers can produce triggers that deviate markedly in form and shape from any known attack, sidestepping existing blacklist-based detection and sanitation approaches.
Language Models (LMs) memorize a vast amount of factual knowledge, exhibiting strong performance across diverse tasks and domains. However, it has been observed that the performance diminishes when dealing with less-popular or low-frequency concepts and entities, for example in domain specific applications. The two prominent approaches to enhance the performance of LMs on low-frequent topics are: Retrieval Augmented Generation (RAG) and fine-tuning (FT) over synthetic data. This paper explores and evaluates the impact of RAG and FT on customizing LMs in handling low-frequency entities on question answering tasks. We conduct extensive experiments on twelve LMs of varying size and type and different fine tuning, data augmentation, and retrieval models. Our findings indicate that while FT boosts the performance across entities of varying popularity, RAG surpasses FT by a large margin particularly for least popular factual knowledge. Additionally, the success of both RAG and FT approaches is amplified by improving retrieval and data augmentation techniques. Fine tuning, while beneficial for small LMs, requires extensive resources. To address this issue, we propose the new Stimulus RAG approach that surpasses the effectiveness of fine tuning based approaches, thereby eliminating the need for the costly data augmentation and fine tuning step for enriching LMs with less popular factual knowledge. The code is available at \url{https://github.com/informagi/RAGvsFT}.
This paper presents our contributions towards advancing the state of Vietnamese language understanding and generation through the development and dissemination of open datasets and pre-trained models for Vietnamese Retrieval-Augmented Generation (RAG) and Large Language Models (LLMs).
The rise of large language models (LLMs) has significantly transformed both the construction and application of information retrieval (IR) systems. However, current interactions between IR systems and LLMs remain limited, with LLMs merely serving as part of components within IR systems, and IR systems being constructed independently of LLMs. This separated architecture restricts knowledge sharing and deep collaboration between them. In this paper, we introduce Self-Retrieval, a novel end-to-end LLM-driven information retrieval architecture. Self-Retrieval unifies all essential IR functions within a single LLM, leveraging the inherent capabilities of LLMs throughout the IR process. Specifically, Self-Retrieval internalizes the retrieval corpus through self-supervised learning, transforms the retrieval process into sequential passage generation, and performs relevance assessment for reranking. Experimental results demonstrate that Self-Retrieval not only outperforms existing retrieval approaches by a significant margin, but also substantially enhances the performance of LLM-driven downstream applications like retrieval-augmented generation.
Retrieval Augmented Generation (RAG) systems have seen huge popularity in augmenting Large-Language Model (LLM) outputs with domain specific and time sensitive data. Very recently a shift is happening from simple RAG setups that query a vector database for additional information with every user input to more sophisticated forms of RAG. However, different concrete approaches compete on mostly anecdotal evidence at the moment. In this paper we present a rigorous dataset creation and evaluation workflow to quantitatively compare different RAG strategies. We use a dataset created this way for the development and evaluation of a boolean agent RAG setup: A system in which a LLM can decide whether to query a vector database or not, thus saving tokens on questions that can be answered with internal knowledge. We publish our code and generated dataset online.
Artificial intelligence (AI) has gained significant attention in healthcare consultation due to its potential to improve clinical workflow and enhance medical communication. However, owing to the complex nature of medical information, large language models (LLM) trained with general world knowledge might not possess the capability to tackle medical-related tasks at an expert level. Here, we introduce EyeGPT, a specialized LLM designed specifically for ophthalmology, using three optimization strategies including role-playing, finetuning, and retrieval-augmented generation. In particular, we proposed a comprehensive evaluation framework that encompasses a diverse dataset, covering various subspecialties of ophthalmology, different users, and diverse inquiry intents. Moreover, we considered multiple evaluation metrics, including accuracy, understandability, trustworthiness, empathy, and the proportion of hallucinations. By assessing the performance of different EyeGPT variants, we identify the most effective one, which exhibits comparable levels of understandability, trustworthiness, and empathy to human ophthalmologists (all Ps>0.05). Overall, ur study provides valuable insights for future research, facilitating comprehensive comparisons and evaluations of different strategies for developing specialized LLMs in ophthalmology. The potential benefits include enhancing the patient experience in eye care and optimizing ophthalmologists' services.
Large language models (LLMs) like ChatGPT demonstrate the remarkable progress of artificial intelligence. However, their tendency to hallucinate -- generate plausible but false information -- poses a significant challenge. This issue is critical, as seen in recent court cases where ChatGPT's use led to citations of non-existent legal rulings. This paper explores how Retrieval-Augmented Generation (RAG) can counter hallucinations by integrating external knowledge with prompts. We empirically evaluate RAG against standard LLMs using prompts designed to induce hallucinations. Our results show that RAG increases accuracy in some cases, but can still be misled when prompts directly contradict the model's pre-trained understanding. These findings highlight the complex nature of hallucinations and the need for more robust solutions to ensure LLM reliability in real-world applications. We offer practical recommendations for RAG deployment and discuss implications for the development of more trustworthy LLMs.
The task of converting natural language queries into SQL queries is intricate, necessitating a blend of precise techniques for an accurate translation. The DIN-SQL (Decomposed-In-Context SQL) methodology represents a significant development in this domain. This paper introduces DFIN (Decomposed Focused-In-Context), an innovative extension of DIN-SQL that enhances Text-to-SQL conversion by addressing schema linking errors, which are a major source of inaccuracies. DFIN uniquely alternates between prompting techniques and Retrieval-Augmented Generation (RAG), adapting to the size and complexity of the database schema. A preprocessing phase embeds database definitions and leverages annotated files, akin to those in the BIRD dataset, facilitating the runtime retrieval of pertinent schema information. This strategy significantly reduces the token count for schema linking prompts, enabling the use of a standard GPT-4 model over its larger context variant, thus handling large-scale databases more effectively and economically. Our evaluation on the BIRD dataset, a challenging real-world benchmark, demonstrates that DFIN not only scales efficiently but also improves accuracy, achieving a score of 51.69. This improvement surpasses DIN-SQL method (the current third-place), which is the highest-ranked model employing in-context learning rather than fine-tuning, previously scoring 50.72. The advancement of DFIN underscores the evolving capabilities of in-context learning methodologies combined with advanced language models, offering a promising avenue for future research in complex Text-to-SQL conversion tasks.
Advancements in model algorithms, the growth of foundational models, and access to high-quality datasets have propelled the evolution of Artificial Intelligence Generated Content (AIGC). Despite its notable successes, AIGC still faces hurdles such as updating knowledge, handling long-tail data, mitigating data leakage, and managing high training and inference costs. Retrieval-Augmented Generation (RAG) has recently emerged as a paradigm to address such challenges. In particular, RAG introduces the information retrieval process, which enhances the generation process by retrieving relevant objects from available data stores, leading to higher accuracy and better robustness. In this paper, we comprehensively review existing efforts that integrate RAG technique into AIGC scenarios. We first classify RAG foundations according to how the retriever augments the generator, distilling the fundamental abstractions of the augmentation methodologies for various retrievers and generators. This unified perspective encompasses all RAG scenarios, illuminating advancements and pivotal technologies that help with potential future progress. We also summarize additional enhancements methods for RAG, facilitating effective engineering and implementation of RAG systems. Then from another view, we survey on practical applications of RAG across different modalities and tasks, offering valuable references for researchers and practitioners. Furthermore, we introduce the benchmarks for RAG, discuss the limitations of current RAG systems, and suggest potential directions for future research. Github: https://github.com/PKU-DAIR/RAG-Survey.
In the domain of digital information dissemination, search engines act as pivotal conduits linking information seekers with providers. The advent of chat-based search engines utilizing Large Language Models (LLMs) and Retrieval Augmented Generation (RAG), exemplified by Bing Chat, marks an evolutionary leap in the search ecosystem. They demonstrate metacognitive abilities in interpreting web information and crafting responses with human-like understanding and creativity. Nonetheless, the intricate nature of LLMs renders their "cognitive" processes opaque, challenging even their designers' understanding. This research aims to dissect the mechanisms through which an LLM-powered chat-based search engine, specifically Bing Chat, selects information sources for its responses. To this end, an extensive dataset has been compiled through engagements with New Bing, documenting the websites it cites alongside those listed by the conventional search engine. Employing natural language processing (NLP) techniques, the research reveals that Bing Chat exhibits a preference for content that is not only readable and formally structured, but also demonstrates lower perplexity levels, indicating a unique inclination towards text that is predictable by the underlying LLM. Further enriching our analysis, we procure an additional dataset through interactions with the GPT-4 based knowledge retrieval API, unveiling a congruent text preference between the RAG API and Bing Chat. This consensus suggests that these text preferences intrinsically emerge from the underlying language models, rather than being explicitly crafted by Bing Chat's developers. Moreover, our investigation documents a greater similarity among websites cited by RAG technologies compared to those ranked highest by conventional search engines.