Accelerating Retrieval-Augmented Generation

An evolving solution to address hallucination and enhance accuracy in large language models (LLMs) is Retrieval-Augmented Generation (RAG), which involves augmenting LLMs with information retrieved from an external knowledge source, such as the web. This paper profiles several RAG execution pipelines and demystifies the complex interplay between their retrieval and generation phases. We demonstrate that while exact retrieval schemes are expensive, they can reduce inference time compared to approximate retrieval variants because an exact retrieval model can send a smaller but more accurate list of documents to the generative model while maintaining the same end-to-end accuracy. This observation motivates the acceleration of the exact nearest neighbor search for RAG. In this work, we design Intelligent Knowledge Store (IKS), a type-2 CXL device that implements a scale-out near-memory acceleration architecture with a novel cache-coherent interface between the host CPU and near-memory accelerators. IKS offers 13.4-27.9x faster exact nearest neighbor search over a 512GB vector database compared with executing the search on Intel Sapphire Rapids CPUs. This higher search performance translates to 1.7-26.3x lower end-to-end inference time for representative RAG applications. IKS is inherently a memory expander; its internal DRAM can be disaggregated and used for other applications running on the server to prevent DRAM, which is the most expensive component in today's servers, from being stranded.

Future of Information Retrieval Research in the Age of Generative AI

In the fast-evolving field of information retrieval (IR), the integration of generative AI technologies such as large language models (LLMs) is transforming how users search for and interact with information. Recognizing this paradigm shift at the intersection of IR and generative AI (IR-GenAI), a visioning workshop supported by the Computing Community Consortium (CCC) was held in July 2024 to discuss the future of IR in the age of generative AI. This workshop convened 44 experts in information retrieval, natural language processing, human-computer interaction, and artificial intelligence from academia, industry, and government to explore how generative AI can enhance IR and vice versa, and to identify the major challenges and opportunities in this rapidly advancing field. This report contains a summary of discussions as potentially important research topics and contains a list of recommendations for academics, industry practitioners, institutions, evaluation campaigns, and funding agencies.

Memory Augmented Cross-encoders for Controllable Personalized Search

Personalized search represents a problem where retrieval models condition on historical user interaction data in order to improve retrieval results. However, personalization is commonly perceived as opaque and not amenable to control by users. Further, personalization necessarily limits the space of items that users are exposed to. Therefore, prior work notes a tension between personalization and users' ability for discovering novel items. While discovery of novel items in personalization setups may be resolved through search result diversification, these approaches do little to allow user control over personalization. Therefore, in this paper, we introduce an approach for controllable personalized search. Our model, CtrlCE presents a novel cross-encoder model augmented with an editable memory constructed from users historical items. Our proposed memory augmentation allows cross-encoder models to condition on large amounts of historical user data and supports interaction from users permitting control over personalization. Further, controllable personalization for search must account for queries which don't require personalization, and in turn user control. For this, we introduce a calibrated mixing model which determines when personalization is necessary. This allows system designers using CtrlCE to only obtain user input for control when necessary. In multiple datasets of personalized search, we show CtrlCE to result in effective personalization as well as fulfill various key goals for controllable personalized search.

Personalization of Large Language Models: A Survey

Personalization of Large Language Models (LLMs) has recently become increasingly important with a wide range of applications. Despite the importance and recent progress, most existing works on personalized LLMs have focused either entirely on (a) personalized text generation or (b) leveraging LLMs for personalization-related downstream applications, such as recommendation systems. In this work, we bridge the gap between these two separate main directions for the first time by introducing a taxonomy for personalized LLM usage and summarizing the key differences and challenges. We provide a formalization of the foundations of personalized LLMs that consolidates and expands notions of personalization of LLMs, defining and discussing novel facets of personalization, usage, and desiderata of personalized LLMs. We then unify the literature across these diverse fields and usage scenarios by proposing systematic taxonomies for the granularity of personalization, personalization techniques, datasets, evaluation methods, and applications of personalized LLMs. Finally, we highlight challenges and important open problems that remain to be addressed. By unifying and surveying recent research using the proposed taxonomies, we aim to provide a clear guide to the existing literature and different facets of personalization in LLMs, empowering both researchers and practitioners.

Learning to Rank for Multiple Retrieval-Augmented Models through Iterative Utility Maximization

This paper investigates the design of a unified search engine to serve multiple retrieval-augmented generation (RAG) agents, each with a distinct task, backbone large language model (LLM), and retrieval-augmentation strategy. We introduce an iterative approach where the search engine generates retrieval results for these RAG agents and gathers feedback on the quality of the retrieved documents during an offline phase. This feedback is then used to iteratively optimize the search engine using a novel expectation-maximization algorithm, with the goal of maximizing each agent's utility function. Additionally, we adapt this approach to an online setting, allowing the search engine to refine its behavior based on real-time individual agents feedback to better serve the results for each of them. Experiments on diverse datasets from the Knowledge-Intensive Language Tasks (KILT) benchmark demonstrates that our approach significantly on average outperforms competitive baselines across 18 RAG models. We also demonstrate that our method effectively ``personalizes'' the retrieval process for each RAG agent based on the collected feedback. Finally, we provide a comprehensive ablation study to explore various aspects of our method.

CS4: Measuring the Creativity of Large Language Models Automatically by Controlling the Number of Story-Writing Constraints

Evaluating the creativity of large language models (LLMs) in story writing is difficult because LLM-generated stories could seemingly look creative but be very similar to some existing stories in their huge and proprietary training corpus. To overcome this challenge, we introduce a novel benchmark dataset with varying levels of prompt specificity: CS4 ($\mathbf{C}$omparing the $\mathbf{S}$kill of $\mathbf{C}$reating $\mathbf{S}$tories by $\mathbf{C}$ontrolling the $\mathbf{S}$ynthesized $\mathbf{C}$onstraint $\mathbf{S}$pecificity). By increasing the number of requirements/constraints in the prompt, we can increase the prompt specificity and hinder LLMs from retelling high-quality narratives in their training data. Consequently, CS4 empowers us to indirectly measure the LLMs' creativity without human annotations. Our experiments on LLaMA, Gemma, and Mistral not only highlight the creativity challenges LLMs face when dealing with highly specific prompts but also reveal that different LLMs perform very differently under different numbers of constraints and achieve different balances between the model's instruction-following ability and narrative coherence. Additionally, our experiments on OLMo suggest that Learning from Human Feedback (LHF) can help LLMs select better stories from their training data but has limited influence in boosting LLMs' ability to produce creative stories that are unseen in the training corpora. The benchmark is released at https://github.com/anirudhlakkaraju/cs4_benchmark.

Comparing Retrieval-Augmentation and Parameter-Efficient Fine-Tuning for Privacy-Preserving Personalization of Large Language Models

Privacy-preserving methods for personalizing large language models (LLMs) are relatively under-explored. There are two schools of thought on this topic: (1) generating personalized outputs by personalizing the input prompt through retrieval augmentation from the user's personal information (RAG-based methods), and (2) parameter-efficient fine-tuning of LLMs per user that considers efficiency and space limitations (PEFT-based methods). This paper presents the first systematic comparison between two approaches on a wide range of personalization tasks using seven diverse datasets. Our results indicate that RAG-based and PEFT-based personalization methods on average yield 14.92% and 1.07% improvements over the non-personalized LLM, respectively. We find that combining RAG with PEFT elevates these improvements to 15.98%. Additionally, we identify a positive correlation between the amount of user data and PEFT's effectiveness, indicating that RAG is a better choice for cold-start users (i.e., user's with limited personal data).

Multimodal Reranking for Knowledge-Intensive Visual Question Answering

Knowledge-intensive visual question answering requires models to effectively use external knowledge to help answer visual questions. A typical pipeline includes a knowledge retriever and an answer generator. However, a retriever that utilizes local information, such as an image patch, may not provide reliable question-candidate relevance scores. Besides, the two-tower architecture also limits the relevance score modeling of a retriever to select top candidates for answer generator reasoning. In this paper, we introduce an additional module, a multi-modal reranker, to improve the ranking quality of knowledge candidates for answer generation. Our reranking module takes multi-modal information from both candidates and questions and performs cross-item interaction for better relevance score modeling. Experiments on OK-VQA and A-OKVQA show that multi-modal reranker from distant supervision provides consistent improvements. We also find a training-testing discrepancy with reranking in answer generation, where performance improves if training knowledge candidates are similar to or noisier than those used in testing.

Retrieval-Enhanced Machine Learning: Synthesis and Opportunities

In the field of language modeling, models augmented with retrieval components have emerged as a promising solution to address several challenges faced in the natural language processing (NLP) field, including knowledge grounding, interpretability, and scalability. Despite the primary focus on NLP, we posit that the paradigm of retrieval-enhancement can be extended to a broader spectrum of machine learning (ML) such as computer vision, time series prediction, and computational biology. Therefore, this work introduces a formal framework of this paradigm, Retrieval-Enhanced Machine Learning (REML), by synthesizing the literature in various domains in ML with consistent notations which is missing from the current literature. Also, we found that while a number of studies employ retrieval components to augment their models, there is a lack of integration with foundational Information Retrieval (IR) research. We bridge this gap between the seminal IR research and contemporary REML studies by investigating each component that comprises the REML framework. Ultimately, the goal of this work is to equip researchers across various disciplines with a comprehensive, formally structured framework of retrieval-enhanced models, thereby fostering interdisciplinary future research.

Interactions with Generative Information Retrieval Systems

At its core, information access and seeking is an interactive process. In existing search engines, interactions are limited to a few pre-defined actions, such as "requery", "click on a document", "scrolling up/down", "going to the next result page", "leaving the search engine", etc. A major benefit of moving towards generative IR systems is enabling users with a richer expression of information need and feedback and free-form interactions in natural language and beyond. In other words, the actions users take are no longer limited by the clickable links and buttons available on the search engine result page and users can express themselves freely through natural language. This can go even beyond natural language, through images, videos, gestures, and sensors using multi-modal generative IR systems. This chapter briefly discusses the role of interaction in generative IR systems. We will first discuss different ways users can express their information needs by interacting with generative IR systems. We then explain how users can provide explicit or implicit feedback to generative IR systems and how they can consume such feedback. Next, we will cover how users interactively can refine retrieval results. We will expand upon mixed-initiative interactions and discuss clarification and preference elicitation in more detail. We then discuss proactive generative IR systems, including context-aware recommendation, following up past conversations, contributing to multi-party conversations, and feedback requests. Providing explanation is another interaction type that we briefly discuss in this chapter. We will also briefly describe multi-modal interactions in generative information retrieval. Finally, we describe emerging frameworks and solutions for user interfaces with generative AI systems.