Collaborative information from user-item interactions is a fundamental source of signal in successful recommender systems. Recently, researchers have attempted to incorporate this knowledge into large language model-based recommender approaches (LLMRec) to enhance their performance. However, there has been little fundamental analysis of whether LLMs can effectively reason over collaborative information. In this paper, we analyze the ability of LLMs to reason about collaborative information in recommendation tasks, comparing their performance to traditional matrix factorization (MF) models. We propose a simple and effective method to improve LLMs’ reasoning capabilities using retrieval-augmented generation (RAG) over the user-item interaction matrix with four different prompting strategies. Our results show that the LLM outperforms the MF model whenever we provide relevant information in a clear and easy-to-follow format, and prompt the LLM to reason based on it. We observe that with this strategy, in almost all cases, the more information we provide, the better the LLM performs.

Understanding user intents in information access scenarios can help us provide more relevant and personalized search results and recommendations. However, analyzing user intents is not easy, especially for emerging forms of Web search such as Artificial Intelligence (AI)-driven chat. To understand user intents from retrospective log data, we need a way to label them with meaningful categories that capture their diversity and dynamics. Existing methods rely on manual or Machine-Learned (ML) labeling, which is either expensive or inflexible for large and dynamic datasets. Large Language Models (LLMs) could generate rich and relevant concepts, descriptions, and examples for user intents using log data of user interactions. However, using LLMs to generate a user intent taxonomy and applying it for a given Information Retrieval (IR) application can be problematic for two main reasons: (1) such a taxonomy is not externally validated; and (2) there may be an undesirable feedback loop if an LLM does both these tasks without external validation. To address this, we propose a new methodology with human experts and assessors to verify the quality of the LLM-generated taxonomy. We also present an end-to-end pipeline that uses an LLM with Human-in-the-Loop (HITL) to produce, refine, and apply labels for user intent analysis in log data. We demonstrate its effectiveness by uncovering new insights into user intents from search and chat logs from the Microsoft Bing Web search engine. The novelty in this research stems from the method for generating purpose-driven user intent taxonomies with strong validation. Our approach not only helps remove methodological and practical bottlenecks from intent-focused research, but also provides a new framework for generating, validating, and applying other kinds of taxonomies in a scalable and adaptable way, with reasonable human effort.

When information retrieval systems return a ranked list of results in response to a query, they may be choosing from a large set of candidate results that are equally useful and relevant. This means we might be able to identify a difference between rankers A and B, where ranker A systematically prefers a certain type of relevant results. Ranker A may have this systematic difference (different “vibe”) without having systematically better or worse results according to standard information retrieval metrics. We first show that a vibe difference can exist, comparing two publicly available rankers, where the one that is trained on health-related queries will systematically prefer health-related results, even for non-health queries. We define a vibe metric that lets us see the words that a ranker prefers. We investigate the vibe of search engine clicks vs. human labels. We perform an initial study into correcting for vibe differences to make ranker A more like ranker B via changes in negative sampling during training.

Conversational search and recommendation systems can ask clarifying questions through the conversation and collect valuable information from users. However, an important question remains: how can we extract relevant information from the user's utterances and use it in the retrieval or recommendation in the next turn of the conversation? Utilizing relevant information from users' utterances leads the system to better results at the end of the conversation. In this paper, we propose a model based on reinforcement learning, namely RelInCo, which takes the user's utterances and the context of the conversation and classifies each word in the user's utterances as belonging to the relevant or non-relevant class. RelInCo uses two Actors: 1) Arrangement-Actor, which finds the most relevant order of words in user's utterances, and 2) Selector-Actor, which determines which words, in the order provided by the arrangement Actor, can bring the system closer to the target of the conversation. In this way, we can find relevant information in the user's utterance and use it in the conversation. The objective function in our model is designed in such a way that it can maximize any desired retrieval and recommendation metrics (i.e., the ultimate

We propose RelQuest, a conversational product search model based on reinforcement learning to generate questions from product descriptions in each round of the conversation, directly maximizing any desired metrics (i.e., the ultimate goal of the conversation), objectives, or even an arbitrary user satisfaction signal. By enabling systems to ask questions about user needs, conversational product search has gained increasing attention in recent years. Asking the right questions through conversations helps the system collect valuable feedback to create better user experiences and ultimately increase sales. In contrast, existing conversational product search methods are based on an assumption that there is a set of effectively pre-defined candidate questions for each product to be asked. Moreover, they make strong assumptions to estimate the value of questions in each round of the conversation. Estimating the true value of questions in each round of the conversation is not trivial since it is unknown. Experiments on real-world user purchasing data show the effectiveness of RelQuest at generating questions that maximize standard evaluation measures such as NDCG.

We propose AC-CRS, a novel conversational recommendation system based on reinforcement learning that better models user interaction compared to prior work. Interactive recommender systems expect an initial request from a user and then iterate by asking questions or recommending potential matching items, continuing until some stopping criterion is achieved. Unlike most existing works that stop as soon as an item is recommended, we model the more realistic expectation that the interaction will continue if the item is not appropriate. Using this process, AC-CRS is able to support a more flexible conversation with users. Unlike existing models, AC-CRS is able to estimate a value for each question in the conversation to make sure that questions asked by the agent are relevant to the target item (i.e., user needs). We also model the possibility that the system could suggest more than one item in a given turn, allowing it to take advantage of screen space if it is present. AC-CRS also better accommodates the massive space of items that a real-world recommender system must handle. Experiments on real-world user purchasing data show the effectiveness of our model in terms of standard evaluation measures such as NDCG.

We present RML, the first known general reinforcement learning framework for relevance feedback that directly optimizes any desired retrieval metric, including precision-oriented, recall-oriented, and even diversity metrics: RML can be easily extended to directly optimize any arbitrary user satisfaction signal. Using the RML framework, we can select effective feedback terms and weight them appropriately, improving on past methods that fit parameters to feedback algorithms using heuristic approaches or methods that do not directly optimize for retrieval performance. Learning an effective relevance feedback model is not trivial since the true feedback distribution is unknown. Experiments on standard TREC collections compare RML to existing feedback algorithms, demonstrate the effectiveness of RML at optimizing for MAP and α-n DCG, and show the impact on related measures.

Axiomatic analysis is a well-defined theoretical framework for analytical evaluation of information retrieval models. The current studies in axiomatic analysis implicitly assume that the constraints (axioms) are independent. In this paper, we revisit this assumption and hypothesize that there might be interdependence relationships between the existing constraints. As a preliminary study, we focus on the pseudo-relevance feedback (PRF) models that have been theoretically studied using the axiomatic analysis approach. In this paper, we introduce two novel interdependent PRF constraints which emphasize on the effect of existing constraints on each other. We further modify two state-of-the-art PRF models, log-logistic and relevance models, in order to satisfy the proposed constraints. Experiments on three TREC newswire and web collections demonstrate that the proposed modifications significantly outperform the baselines, in all cases.

Number of terms in a query is a query-specific constant that is typically ignored in retrieval functions. However, previous studies have shown that the performance of retrieval models varies for different query lengths, and it usually degrades when query length increases. A possible reason for this issue can be the extraneous terms in longer queries that makes it a challenge for the retrieval models to distinguish between the key and complementary concepts of the query. As a signal to understand the importance of a term, inverse document frequency (IDF) can be used to discriminate query terms. In this paper, we propose a constraint to model the interaction between query length and IDF. Our theoretical analysis shows that current state-of-the-art retrieval models, such as BM25, do not satisfy the proposed constraint. We further analyze the BM25 model and suggest a modification to adapt BM25 so that it adheres to the new constraint. Our experiments on three TREC collections demonstrate that the proposed modification outperforms the baselines, especially for verbose queries.

Pseudo-relevance feedback (PRF) refers to a query expansion strategy based on top-retrieved documents, which has been shown to be highly effective in many retrieval models. Previous work has introduced a set of constraints (axioms) that should be satisfied by any PRF model. In this paper, we propose three additional constraints based on the proximity of feedback terms to the query terms in the feedback documents. As a case study, we consider the log-logistic model, a state-of-the-art PRF model that has been proven to be a successful method in satisfying the existing PRF constraints, and show that it does not satisfy the proposed constraints. We further modify the log-logistic model based on the proposed proximity-based constraints. Experiments on four TREC collections demonstrate the effectiveness of the proposed constraints. Our modification the log-logistic model leads to significant and substantial (up to 15%) improvements. Furthermore, we show that the proposed proximity-based function outperforms the well-known Gaussian kernel which does not satisfy all the proposed constraints.

Pseudo-relevance feedback (PRF) has been proven to be an effective query expansion strategy to improve retrieval performance. Several PRF methods have so far been proposed for many retrieval models. Recent theoretical studies of PRF methods show that most of the PRF methods do not satisfy all necessary constraints. Among all, the log-logistic model has been shown to be an effective method that satisfies most of the PRF constraints. In this paper, we first introduce two new PRF constraints. We further analyze the log-logistic feedback model and show that it does not satisfy these two constraints as well as the previously proposed "relevance effect" constraint. We then modify the log-logistic formulation to satisfy all these constraints. Experiments on three TREC newswire and web collections demonstrate that the proposed modification significantly outperforms the original log-logistic model, in all collections.