Conversational Recommender Systems (CRSs) facilitate item discovery through multi-turn dialogues that elicit user preferences via natural language interaction. This field has gained significant attention following advancements in Natural Language Processing (NLP) enabled by Large Language Models (LLMs). However, current CRS research remains constrained by datasets with fundamental limitations. Human-generated datasets suffer from inconsistent dialogue quality, limited domain expertise, and insufficient scale for real-world application, while synthetic datasets created with proprietary LLMs ignore the diversity of real-world user behavior and present significant barriers to accessibility and reproducibility. The development of effective CRSs depends critically on addressing these deficiencies.To this end, we present DistillRecDial, a novel conversational recommendation dataset generated through a knowledge distillation pipeline that leverages smaller, more accessible open LLMs. Crucially, DistillRecDial simulates a range of user types with varying intentions, preference expression styles, and initiative levels, capturing behavioral diversity that is largely absent from prior work. Human evaluation demonstrates that our dataset significantly outperforms widely adopted CRS datasets in dialogue coherence and domain-specific expertise, indicating its potential to advance the development of more realistic and effective conversational recommender systems.

Recommender systems (RSs) have become increasingly versatile, finding applications across diverse domains.Large Language Models (LLMs) significantly contribute to this advancement since the vast amount of knowledge embedded in these models can be easily exploited to provide users with high-quality recommendations.However, current RSs based on LLMs have room for improvement.As an example, knowledge injection techniques can be used to finetune LLMs by incorporating additional data, thus improving their performance on downstream tasks.In a recommendation setting, these techniques can be exploited to incorporate further knowledge, which can result in a more accurate representation of the items.Accordingly, in this paper, we propose a pipeline for knowledge injection specifically designed for RS.First, we incorporate external knowledge by drawing on three sources: (a) knowledge graphs; (b) textual descriptions; (c) collaborative information about user interactions.Next, we lexicalize the knowledge, and we instruct and fine-tune an LLM, which can easily return a list of recommendations.Extensive experiments on movie, music, and book datasets validate our approach.Moreover, the experiments showed that knowledge injection is particularly needed in domains (i.e., music and books) where the encoded knowledge within LLMs may not be suitable for recommendation tasks, even if such content was used during the training of the model.This finding points to several promising future research directions.

Traditional recommender systems (RSs) generate suggestions by relying on user preferences and item characteristics. However, they do not to properly involve the user in the decision-making process. This gap is particularly evident in Conversational Recommender Systems (CRSs), where existing methods struggle to facilitate meaningful dialogue and dynamic user interactions.

Given the rising global concerns about healthy nutrition and environmental sustainability, individuals need more and more support in making good choices concerning their daily meals. To this end, in this paper we introduce HeaSE, a framework for Healthy And Sustainable Eating. Given an input recipe, HeaSE identifies healthier and more sustainable meals by exploiting retrieval techniques and large language models. The framework works in two steps. First, it uses food retrieval strategies based on macro-nutrient information to identify candidate alternative meals. This ensures that the substitutions maintain a similar nutritional profile. Next, HeaSE employs large language models to re-rank these potential replacements while considering factors beyond just nutrition, such as the recipe’s environmental impact. In the experimental evaluation, we showed the capabilities of LLMs in identifying more sustainable and healthier alternatives within a set of candidate options. This highlights the potential of these models to guide users towards food choices that are both nutritious and environmentally responsible.

In this paper, we present a strategy to provide users with explainable cross-domain recommendations (CDR) that exploits large language models (LLMs). Generally speaking, CDR is a task that is hard to tackle, mainly due to data sparsity issues. Indeed, CDR models require a large amount of data labeled in both source and target domains, which are not easy to collect. Accordingly, our approach relies on the intuition that the knowledge that is already encoded in LLMs can be used to more easily bridge the domains and seamlessly provide users with personalized cross-domain suggestions.

Conversational Recommender Systems (CRS) have recently drawn attention due to their capacity of delivering personalized recommendations through multi-turn natural language interactions. In this paper, we fit into this research line and we introduce a Knowledge-Aware Sequential Conversational Recommender System (KASCRS) that exploits transformers and knowledge graph embeddings to provide users with recommendations in a conversational setting.