CIKM 2026 · ROME, ITALY

EARL Workshop 2026

CO-LOCATED WITH CIKM 2026 Rome, Italy

EARL 2026 is the 3rd Workshop on Evaluating and Applying Recommender Systems with Large Language Models. Co-located with the 35th International ACM Conference on Knowledge and Information Management (CIKM 2026), the workshop brings together researchers and practitioners working at the intersection of large language models (LLMs) and recommender systems (RSs).

The workshop will be held in person in Rome, Italy. We will focus on the evaluation, reproducibility, practical deployment, and responsible integration of LLM-driven recommender systems, while welcoming exploratory work and critical discussion.

Host conference CIKM 2026

Location Rome, Italy

Workshop date 8 November 2026

Format Half-day · In Person Only

35th International ACM Conference on Knowledge and Information Management

THE 2026 EDITION

Schedule

Sunday, 8 November 2026 · Rome, Italy

All times are local Rome time (CET, UTC+1).

09:00–09:10	Opening remarks & Best Paper Award ceremony Guillaume Salha-Galvan and Sairamvinay Vijayaraghavan
09:10–09:40	Invited talk Invited talk (title to be announced) Bum Jun Kim (The University of Tokyo) 25 min presentation + 5 min Q&A
09:40–10:00	Long talk Paper ID 2 Beyond Posts: Recommending Conversations in Threads Feed Xiuyan Ni, Qing Feng, Eric He, Akhil Nadigatla, Adam Kozdrowicz, Emerson Wenzel, Runbo Jiang, Nicholas Joodi, Xiaoyu Cao, Zichao Li, Joy Qiu, Shuting Wang, Shujian Bu and Ivan Ji 15 min presentation + 5 min Q&A
10:00–10:10	Short talk Paper ID 3 From Raw IDs to Semantic Planning: How Recommender Systems Utilize Information at Scale Changhong Jin, Shiqiu Yang, Roger Zhe Li, Yingjie Niu, Aghiles Salah, Mete Sertkan, Zheng Ju, Xingsheng Guo, Huifeng Guo, Ruihai Dong and Barry Smyth 8 min presentation + 2 min Q&A
10:10–10:20	Short talk Paper ID 6 Encoded but Exposed: Language Embeddings can Reveal More Than They Should in Recommender Systems Linda Beková and Rodrigo Alves 8 min presentation + 2 min Q&A
10:20–10:30	Short talk Paper ID 13 When to Ask: A Framework for Interruption-Aware Conversational Recommendation Sanjana Arun 8 min presentation + 2 min Q&A
10:30–10:40	Short talk Paper ID 16 Validity Lag: Why LLM Recommender Evaluation Keeps Failing the Same Way Shiming Xie 8 min presentation + 2 min Q&A
10:40–11:30	Coffee break
11:30–11:50	Long talk Paper ID 4 Dialogue Generation for Conversational Recommendation Using User Search Interactions and Knowledge Graphs Donggyu Yoon, Minsung Hwang, Kwanghee Jang, Gowoon Hwang and Joyce Jiyoung Whang 15 min presentation + 5 min Q&A
11:50–12:10	Long talk Paper ID 12 Format Compliance without Detectable Preference Gain: A Paired Audit of Post-Trained LLM Recommenders Shiming Xie 15 min presentation + 5 min Q&A
12:10–12:20	Short talk Paper ID 15 Persona Aware Session-Based Recommendation with LLM-Enhanced Knowledge Graphs Muskan Gupta, Priyanka Gupta and Jyotsana Khatri 8 min presentation + 2 min Q&A
12:20–12:30	Short talk Paper ID 5 From a Large-Scale Teacher to Efficient Multimodal Students for Search Relevance Prediction Tomasz Gniazdowski, Mohammadreza Momenifar, Nadia Vase, Shahram Khadivi, Wiktor Walentynowicz, Nicola Ueffing, Jan Pawłowski, Piotr Szymański and Abraham Bagherjeiran 8 min presentation + 2 min Q&A
12:30–12:40	Short talk Paper ID 8 Preprocessing Choices in Fine-Tuning Data Matter: Utility and Demographic Sensitivity in LLM-Based Recommendation Furkan Yasir Goksu, Yaren Yilmaz and Şule Gündüz Öğüdücü 8 min presentation + 2 min Q&A
12:40–12:50	Short talk Paper ID 10 Revisiting Generative vs. Dense Retrieval: A Static Value Prior Reverses the Gap Renbo Tu, Yang Liu and Shuying Sun 8 min presentation + 2 min Q&A
12:50–12:55	Closing remarks Guillaume Salha-Galvan and Sairamvinay Vijayaraghavan

EARL Workshop 2026

Schedule

Sunday, 8 November 2026 · Rome, Italy

EARL Workshop

SUPPORTERS

CONTACT

PREVIOUS WORKSHOPS