Recommendation Systems & LLMs

Large Language Models (LLMs) have advanced recommendation through enhanced reasoning, but their massive scale poses significant challenges for real-world deployment due to high inference costs. Conversely, while Small Language Models (SLMs) offer an efficient alternative, their reasoning capabilities for recommendation remain under-explored. Existing systems often use natural language rationales merely as unsupervised descriptive text, failing to harness their full potential as learning signals. In this work our main idea is to create a common understanding of user and items across multiple domains called Thought Space with SLM instead of using LLM¡¯s distilled knowledge. To that end we propose PULSE (Preference Understanding by Latent Semantic Embeddings), a framework that treats SLM-generated rationales as first class views, supervising them with interaction histories to jointly model user actions (what) and their semantic drivers (why). Existing methods consider only interactions such as sequences and embeddings, whereas PULSE treats rationales as first-class signals, this ingenious design yields embeddings that are more robust and generalizable. Extensive experiments demonstrate that PULSE outperforms leading ID, Collaborative Filtering (CF), and LLM-based sequential recommendation models across multiple benchmark datasets. Furthermore, PULSE exhibits superior transferability in cross-domain recommendation and shows strong performance on downstream tasks such as reasoning-oriented question answering.

Implicit feedback -- the main data source for training Recommender Systems (RSs) -- is inherently noisy and has been shown to negatively affect recommendation effectiveness. Denoising has been proposed as a method for removing noisy implicit feedback and improving recommendations. Prior work has focused on \emph{in-training} denoising, however this requires additional data, changes to the model architecture and training procedure or fine-tuning, all of which can be costly and data hungry. In this work, we focus on \emph{post-training} denoising. Different from in-training denoising, post-training denoising does not involve changing the architecture of the model nor its training procedure, and does not require additional data. Specifically, we present a method for post-training denoising user profiles using Large Language Models (LLMs) for Collaborative Filtering (CF) recommendations. Our approach prompts LLMs with (i) a user profile (user interactions), (ii) a candidate item, and (iii) its rank as given by the CF recommender, and asks the LLM to remove items from the user profile to improve the rank of the candidate item. Experiments with a state-of-the-art CF recommender and 4 open and closed source LLMs in 3 datasets show that our denoising yields improvements up to 13\% in effectiveness over the original user profiles.

Recent advances in large language models (LLMs) have opened new opportunities for personalized news recommendation. However, existing LLM-based approaches mainly focus on semantic enrichment while overlooking structural signals such as entity-level relations that are crucial for modeling user preferences. Meanwhile, graph-based methods capture structural information but often rely on sparse click-based or incomplete news¨Centity interactions, limiting their ability to model rich relational structures. To address these limitations, we propose PromptHG, a unified framework that integrates LLM prompting with heterogeneous graph learning for news recommendation. First, PromptHG leverages LLMs to directly synthesize entities from news titles and link articles through shared entity nodes, uncovering relationships beyond conventional interaction signals and alleviating sparsity in user behavior data. Second, we construct a heterogeneous news¨Centity graph that integrates user click sequences with entity-based connections, and employ a lightweight graph encoder to learn robust news and user representations, enabling the model to capture complex structural dependencies for improved preference modeling. Extensive experiments on two benchmark datasets demonstrate that PromptHG consistently outperforms strong baselines across multiple evaluation metrics, highlighting the effectiveness of LLM-guided entity synthesis and heterogeneous graph modeling for personalized news recommendation.

Training Conversational recommender systems (CRS) requires extensive dialogue data, which is challenging to collect at scale. To address this, researchers have used simulated user-recommender conversations. Traditional simulation approaches often utilize a single large language model (LLM) that generates entire conversations with prior knowledge of the target items, leading to scripted and artificial dialogues. We propose a reference-free simulation framework that trains two independent LLMs, one as the user and one as the conversational recommender. These models interact in real-time without access to predetermined target items, but preference summaries and target attributes, enabling the recommender to genuinely infer user preferences through dialogue. This approach produces more realistic and diverse conversations that closely mirror authentic human-AI interactions. Our reference-free simulators match or exceed existing methods in quality, while offering a scalable solution for generating high-quality conversational recommendation data without constraining conversations to pre-defined target items. We conduct both quantitative and human evaluation to confirm the effectiveness of our reference-free approach.

We tackle the challenge of integrating large language models (LLMs) with external recommender systems to enhance domain expertise in conversational recommendation (CRS). Current LLM-based CRS approaches primarily rely on zero/few-shot methods for generating item recommendations based on user queries, but this method faces two significant challenges: (1) without domain-specific adaptation, LLMs frequently recommend items not in the target item space, resulting in low recommendation accuracy; and (2) LLMs largely rely on dialogue context for content-based recommendations, neglecting the collaborative relationships among item sequences. To address these limitations, we introduce the CARE (Contextual Adaptation of Recommenders) framework. CARE (a) integrates external recommender systems as domain experts, producing candidate items through entity-level insights, and (b) customizes LLMs as rerankers to enhance the accuracy by leveraging contextual information. Our results demonstrate that incorporating CARE framework significantly enhances recommendation accuracy of LLMs by an average of 54% and 25% for ReDial and INSPIRED datasets. The most effective CARE strategy involves LLMs selecting and reranking candidate items that external recommenders provide based on contextual insights.