TOPIC

Conversational Recommenders

17 synthesis notes · 23 source papers

View as

Why do queries and their causes seem semantically different?

Information retrieval systems find passages matching query language, but what if the segment that actually caused a user's question says something quite different? This explores when semantic similarity fails to find causal relevance.

What makes conversational recommenders hard to build well?

Most assume the challenge is language fluency, but what if the real problem is managing mixed-initiative dialogue—where both users and systems take turns driving the conversation?

Can language models bridge the gap between critique and preference?

When users express what they dislike rather than what they want, can LLMs reliably transform those critiques into positive preferences that retrieval systems can actually use?

Does conversation order matter for recommending items in dialogue?

Conversational recommendation systems typically ignore the sequence in which items are mentioned, treating dialogue as a bag of entities. But does the order itself carry predictive signal about what to recommend next?

Do simulated training interactions transfer to real conversations?

Most conversational recommender systems train on simulated entity-level exchanges, not natural dialogue. The question is whether models built this way actually work when deployed with real users who speak naturally and deviate from expected patterns.

Can unified policy learning improve conversational recommender systems?

This explores whether formulating attribute-asking, item-recommending, and timing decisions as a single reinforcement learning policy outperforms treating them as separate components. The question matters because joint optimization could improve conversation quality and system scalability.

Can conversational recommenders recover lost preference signals from history?

Conversational recommenders abandoned item and user similarity signals when they shifted to dialogue-focused design. Can integrating historical sessions and look-alike users restore these channels without losing dialogue benefits?

How should LLM-based recommenders retrieve from massive item corpora?

When conversational recommenders need to search millions of items, the LLM cannot memorize the corpus. What retrieval strategies work best under different constraints, and how do they trade off latency, sample efficiency, and scalability?

Where does LLM recommendation bias actually come from?

Do conversational AI systems inherit popularity bias from their training data or from the datasets they're deployed on? Understanding the source matters for knowing how to fix it.

How can LLM agents handle huge candidate lists without breaking?

ReAct agents fail when retrieval tools return hundreds of items that overflow prompts. What architectural changes let LLMs work effectively with large candidate sets in recommendation systems?

Can controlled latent variables make LLM user simulators realistic?

Can session-level and turn-level latent variables steer LLM-based user simulators toward realistic dialogue while maintaining measurable diversity and ground truth labels for training conversational systems?

Do LLMs in conversational recommendation systems use collaborative or content knowledge?

Conversational recommenders powered by LLMs might rely on either collaborative signals (user interaction patterns) or content/context knowledge (semantic understanding). Understanding which signal dominates would reveal how to design and deploy these systems effectively.

Source papers 23

The Arxiv papers behind this sub-topic. Links may take you off-site to arxiv.org.

"It doesn't look good for a date": Transforming Critiques into Preferences for Conversational Recommendation Systems
Conversations aimed at determining good recommendations are iterative in nature. People often express their preferences in terms of a critique of the current recommendation (e.g., “It doesn’t look goo…
A Conversation is Worth A Thousand Recommendations: A Survey of Holistic Conversational Recommender Systems
Conversational recommender systems (CRS) generate recommendations through an interactive process. However, not all CRS approaches use human conversations as their source of interaction data; the major…
A Unified Multi-task Learning Framework for Multi-goal Conversational Recommender Systems
Recent years witnessed several advances in developing multi-goal conversational recommender systems (MG-CRS) that can proactively attract users’ interests and naturally lead user-engaged dialogues wit…
Advances and Challenges in Conversational Recommender Systems: A Survey
Recommender systems exploit interaction history to estimate user preference, having been heavily used in a wide range of industry applications. However, static recommendation models are difficult to a…
Backtracing: Retrieving the Cause of the Query
While information retrieval (IR) systems may provide answers for such user queries, they do not directly assist content creators—such as lecturers who want to improve their content—identify segments t…
Conversational Recommendation: A Grand AI Challenge
First, while conventional recommendations rely on push communication, conversational recommender systems (CRS) support multi-turn and mixed-initiative interaction patterns. Moreover, in particular nat…
Dialoging Resonance: How Users Perceive, Reciprocate and React to Chatbot’s Self-Disclosure in Conversational Recommendations
Using chatbots to deliver recommendations is increasingly popular. The design of recommendation chatbots has primarily been taking an information-centric approach by focusing on the recommended conten…
INSPIRED: Toward Sociable Recommendation Dialog Systems
we present INSPIRED, a new dataset of 1,001 human-human dialogs for movie recommendation with measures for successful recommendations. To better understand how humans make recommendations in communica…
Improving Conversational Recommender Systems via Transformer-based Sequential Modelling
In Conversational Recommender Systems (CRSs), conversations usually involve a set of related items and entities e.g., attributes of items. These items and entities are mentioned in order following the…
Large Language Models as Zero-Shot Conversational Recommenders
(1) Data: To gain insights into model behavior in “in-the-wild” conversational recommendation scenarios, we construct a new dataset of recommendation-related conversations by scraping a popular discus…
Learning to Ask Appropriate Questions in Conversational Recommendation
![A screenshot of a computer](/assets/paper-images/LearningToAskAppropriateQuestions.png) Conversational recommender systems (CRSs) have revolutionized the conventional recommendation paradigm by emb…
Learning to Ask Critical Questions for Assisting Product Search
In this paper, we propose a dual-learning model that hybrids the best from both implicit session feedback and proactively clarifying with users on the most critical questions. Hence, there are two br…
Leveraging Large Language Models in Conversational Recommender Systems
effectively leveraging LLMs within a CRS introduces new technical challenges, including properly understanding and controlling a complex conversation and retrieving from external sources of informatio…
Multi-Task End-to-End Training Improves Conversational Recommendation
“The modern recommendation systems found in commercial applications are largely based on implicit preferences, such as a user’s history of web page clicks, item purchases, or media streams, with the r…
OpinionConv: Conversational Product Search with Grounded Opinions
When searching for products, the opinions of others play an important role in making informed decisions. Subjective experiences about a product can be a valuable source of information. This is also tr…
Rec-R1: Bridging Generative Large Language Models and User-Centric Recommendation Systems via Reinforcement Learning
We propose Rec-R1, a general reinforcement learning framework that bridges large language models (LLMs) with recommendation systems through closed-loop optimization. Unlike prompting and supervised fi…
Recommender AI Agent: Integrating Large Language Models for Interactive Recommendations
However, LLMs lack the knowledge of domain-specific item catalogs and behavioral patterns, particularly in areas that diverge from general world knowledge, such as online e-commerce. Finetuning LLMs f…
RevCore: Review-augmented Conversational Recommendation
CR remains challengeable because (i) typical dialogues are short and lack sufficient item information for user preference capturing (Chen et al., 2019; Zhou et al., 2020), and (ii) difficulties exist …
Topic-Guided Conversational Recommender in Multiple Domains
Conversational recommender systems (CRS) aim to recommend high-quality items to users through interactive conversations. To develop an effective CRS, the support of high-quality datasets is essential.…
Towards Conversational Recommendation over Multi-Type Dialogs
We propose a new task of conversational recommendation over multi-type dialogs, where the bots can proactively and naturally lead a conversation from a non-recommendation dialog (e.g., QA) to a recomm…
Towards Question-based Recommender Systems
Conversational and question-based recommender systems have gained increasing attention in recent years, with users enabled to converse with the system and better control recommendations. Nevertheless,…
Unified Conversational Recommendation Policy Learning via Graph-based Reinforcement Learning
Conversational recommender systems (CRS) enable the traditional recommender systems to explicitly acquire user preferences towards items and attributes through interactive conversations. Reinforcement…
User-Centric Conversational Recommendation with Multi-Aspect User Modeling
Conversational recommender systems (CRS) aim to provide high-quality recommendations in conversations. However, most conventional CRS models mainly focus on the dialogue understanding of the current s…