Abstract:Iterative retrieval-augmented generation (iRAG) models offer an effective approach for multi-hop question answering (QA). However, their retrieval process faces two key challenges: (1) it can be disrupted by irrelevant documents or factually inaccurate chain-of-thoughts; (2) their retrievers are not designed to dynamically adapt to the evolving information needs in multi-step reasoning, making it difficult to identify and retrieve the missing information required at each iterative step. Therefore, we propose KiRAG, which uses a knowledge-driven iterative retriever model to enhance the retrieval process of iRAG. Specifically, KiRAG decomposes documents into knowledge triples and performs iterative retrieval with these triples to enable a factually reliable retrieval process. Moreover, KiRAG integrates reasoning into the retrieval process to dynamically identify and retrieve knowledge that bridges information gaps, effectively adapting to the evolving information needs. Empirical results show that KiRAG significantly outperforms existing iRAG models, with an average improvement of 9.40% in R@3 and 5.14% in F1 on multi-hop QA.
Abstract:Retrieval Augmented Generation (RAG) is a framework for incorporating external knowledge, usually in the form of a set of documents retrieved from a collection, as a part of a prompt to a large language model (LLM) to potentially improve the performance of a downstream task, such as question answering. Different from a standard retrieval task's objective of maximising the relevance of a set of top-ranked documents, a RAG system's objective is rather to maximise their total utility, where the utility of a document indicates whether including it as a part of the additional contextual information in an LLM prompt improves a downstream task. Existing studies investigate the role of the relevance of a RAG context for knowledge-intensive language tasks (KILT), where relevance essentially takes the form of answer containment. In contrast, in our work, relevance corresponds to that of topical overlap between a query and a document for an information seeking task. Specifically, we make use of an IR test collection to empirically investigate whether a RAG context comprised of topically relevant documents leads to improved downstream performance. Our experiments lead to the following findings: (a) there is a small positive correlation between relevance and utility; (b) this correlation decreases with increasing context sizes (higher values of k in k-shot); and (c) a more effective retrieval model generally leads to better downstream RAG performance.
Abstract:While question-like queries are gaining popularity and search engines' users increasingly adopt them, keyphrase search has traditionally been the cornerstone of web search. This query type is also prevalent in specialised search tasks such as academic or professional search, where experts rely on keyphrases to articulate their information needs. However, current dense retrieval models often fail with keyphrase-like queries, primarily because they are mostly trained on question-like ones. This paper introduces a novel model that employs the ColBERT architecture to enhance document ranking for keyphrase queries. For that, given the lack of large keyphrase-based retrieval datasets, we first explore how Large Language Models can convert question-like queries into keyphrase format. Then, using those keyphrases, we train a keyphrase-based ColBERT ranker (ColBERTKP_QD) to improve the performance when working with keyphrase queries. Furthermore, to reduce the training costs associated with training the full ColBERT model, we investigate the feasibility of training only a keyphrase query encoder while keeping the document encoder weights static (ColBERTKP_Q). We assess our proposals' ranking performance using both automatically generated and manually annotated keyphrases. Our results reveal the potential of the late interaction architecture when working under the keyphrase search scenario.
Abstract:In the realm of music recommendation, sequential recommender systems have shown promise in capturing the dynamic nature of music consumption. Nevertheless, traditional Transformer-based models, such as SASRec and BERT4Rec, while effective, encounter challenges due to the unique characteristics of music listening habits. In fact, existing models struggle to create a coherent listening experience due to rapidly evolving preferences. Moreover, music consumption is characterized by a prevalence of repeated listening, i.e., users frequently return to their favourite tracks, an important signal that could be framed as individual or personalized popularity. This paper addresses these challenges by introducing a novel approach that incorporates personalized popularity information into sequential recommendation. By combining user-item popularity scores with model-generated scores, our method effectively balances the exploration of new music with the satisfaction of user preferences. Experimental results demonstrate that a Personalized Most Popular recommender, a method solely based on user-specific popularity, outperforms existing state-of-the-art models. Furthermore, augmenting Transformer-based models with personalized popularity awareness yields superior performance, showing improvements ranging from 25.2% to 69.8%. The code for this paper is available at https://github.com/sisinflab/personalized-popularity-awareness.
Abstract:Transformer-based recommender systems, such as BERT4Rec or SASRec, achieve state-of-the-art results in sequential recommendation. However, it is challenging to use these models in production environments with catalogues of millions of items: scaling Transformers beyond a few thousand items is problematic for several reasons, including high model memory consumption and slow inference. In this respect, RecJPQ is a state-of-the-art method of reducing the models' memory consumption; RecJPQ compresses item catalogues by decomposing item IDs into a small number of shared sub-item IDs. Despite reporting the reduction of memory consumption by a factor of up to 50x, the original RecJPQ paper did not report inference efficiency improvements over the baseline Transformer-based models. Upon analysing RecJPQ's scoring algorithm, we find that its efficiency is limited by its use of score accumulators for each item, which prevents parallelisation. In contrast, LightRec (a non-sequential method that uses a similar idea of sub-ids) reported large inference efficiency improvements using an algorithm we call PQTopK. We show that it is also possible to improve RecJPQ-based models' inference efficiency using the PQTopK algorithm. In particular, we speed up RecJPQ-enhanced SASRec by a factor of 4.5 x compared to the original SASRec's inference method and by a factor of 1.56 x compared to the method implemented in RecJPQ code on a large-scale Gowalla dataset with more than a million items. Further, using simulated data, we show that PQTopK remains efficient with catalogues of up to tens of millions of items, removing one of the last obstacles to using Transformer-based models in production environments with large catalogues.
Abstract:Neural networks -- especially those that use large, pre-trained language models -- have improved search engines in various ways. Most prominently, they can estimate the relevance of a passage or document to a user's query. In this work, we depart from this direction by exploring whether neural networks can effectively predict which of a document's passages are unlikely to be relevant to any query submitted to the search engine. We refer to this query-agnostic estimation of passage relevance as a passage's quality. We find that our novel methods for estimating passage quality allow passage corpora to be pruned considerably while maintaining statistically equivalent effectiveness; our best methods can consistently prune >25% of passages in a corpora, across various retrieval pipelines. Such substantial pruning reduces the operating costs of neural search engines in terms of computing resources, power usage, and carbon footprint -- both when processing queries (thanks to a smaller index size) and when indexing (lightweight models can prune low-quality passages prior to the costly dense or learned sparse encoding step). This work sets the stage for developing more advanced neural "learning-what-to-index" methods.
Abstract:Retrieval-augmented generation (RAG) offers an effective approach for addressing question answering (QA) tasks. However, the imperfections of the retrievers in RAG models often result in the retrieval of irrelevant information, which could introduce noises and degrade the performance, especially when handling multi-hop questions that require multiple steps of reasoning. To enhance the multi-hop reasoning ability of RAG models, we propose TRACE. TRACE constructs knowledge-grounded reasoning chains, which are a series of logically connected knowledge triples, to identify and integrate supporting evidence from the retrieved documents for answering questions. Specifically, TRACE employs a KG Generator to create a knowledge graph (KG) from the retrieved documents, and then uses an Autoregressive Reasoning Chain Constructor to build reasoning chains. Experimental results on three multi-hop QA datasets show that TRACE achieves an average performance improvement of up to 14.03% compared to using all the retrieved documents. Moreover, the results indicate that using reasoning chains as context, rather than the entire documents, is often sufficient to correctly answer questions.
Abstract:Transformer-based Cross-Encoders achieve state-of-the-art effectiveness in text retrieval. However, Cross-Encoders based on large transformer models (such as BERT or T5) are computationally expensive and allow for scoring only a small number of documents within a reasonably small latency window. However, keeping search latencies low is important for user satisfaction and energy usage. In this paper, we show that weaker shallow transformer models (i.e., transformers with a limited number of layers) actually perform better than full-scale models when constrained to these practical low-latency settings since they can estimate the relevance of more documents in the same time budget. We further show that shallow transformers may benefit from the generalized Binary Cross-Entropy (gBCE) training scheme, which has recently demonstrated success for recommendation tasks. Our experiments with TREC Deep Learning passage ranking query sets demonstrate significant improvements in shallow and full-scale models in low-latency scenarios. For example, when the latency limit is 25ms per query, MonoBERT-Large (a cross-encoder based on a full-scale BERT model) is only able to achieve NDCG@10 of 0.431 on TREC DL 2019, while TinyBERT-gBCE (a cross-encoder based on TinyBERT trained with gBCE) reaches NDCG@10 of 0.652, a +51% gain over MonoBERT-Large. We also show that shallow Cross-Encoders are effective even when used without a GPU (e.g., with CPU inference, NDCG@10 decreases only by 3% compared to GPU inference with 50ms latency), which makes Cross-Encoders practical to run even without specialized hardware acceleration.
Abstract:Adaptations of Transformer models, such as BERT4Rec and SASRec, achieve state-of-the-art performance in the sequential recommendation task according to accuracy-based metrics, such as NDCG. These models treat items as tokens and then utilise a score-and-rank approach (Top-K strategy), where the model first computes item scores and then ranks them according to this score. While this approach works well for accuracy-based metrics, it is hard to use it for optimising more complex beyond-accuracy metrics such as diversity. Recently, the GPTRec model, which uses a different Next-K strategy, has been proposed as an alternative to the Top-K models. In contrast with traditional Top-K recommendations, Next-K generates recommendations item-by-item and, therefore, can account for complex item-to-item interdependencies important for the beyond-accuracy measures. However, the original GPTRec paper focused only on accuracy in experiments and needed to address how to optimise the model for complex beyond-accuracy metrics. Indeed, training GPTRec for beyond-accuracy goals is challenging because the interaction training data available for training recommender systems typically needs to be aligned with beyond-accuracy recommendation goals. To solve the misalignment problem, we train GPTRec using a 2-stage approach: in the first stage, we use a teacher-student approach to train GPTRec, mimicking the behaviour of traditional Top-K models; in the second stage, we use Reinforcement Learning to align the model for beyond-accuracy goals. In particular, we experiment with increasing recommendation diversity and reducing popularity bias. Our experiments on two datasets show that in 3 out of 4 cases, GPTRec's Next-K generation approach offers a better tradeoff between accuracy and secondary metrics than classic greedy re-ranking techniques.
Abstract:In Conversational Recommendation Systems (CRS), a user can provide feedback on recommended items at each interaction turn, leading the CRS towards more desirable recommendations. Currently, different types of CRS offer various possibilities for feedback, i.e., natural language feedback, or answering clarifying questions. In most cases, a user simulator is employed for training as well as evaluating the CRS. Such user simulators typically critique the current retrieved items based on knowledge of a single target item. Still, evaluating systems in offline settings with simulators suffers from problems, such as focusing entirely on a single target item (not addressing the exploratory nature of a recommender system), and exhibiting extreme patience (consistent feedback over a large number of turns). To overcome these limitations, we obtain extra judgements for a selection of alternative items in common CRS datasets, namely Shoes and Fashion IQ Dresses. Going further, we propose improved user simulators that allow simulated users not only to express their preferences about alternative items to their original target, but also to change their mind and level of patience. In our experiments using the relative image captioning CRS setting and different CRS models, we find that using the knowledge of alternatives by the simulator can have a considerable impact on the evaluation of existing CRS models, specifically that the existing single-target evaluation underestimates their effectiveness, and when simulated users are allowed to instead consider alternatives, the system can rapidly respond to more quickly satisfy the user.