ACL Findings2026
Beyond Static Profiles: Capturing the Fluidity of User Preferences in Diverse Scenarios
Chunyang Gao, Yi Huang, Jingyu Yao, Xiaoting Wu, Junlan Feng
摘要
Despite the remarkable evolution of Large Language Models (LLMs) from simple assistants to versatile agents, effective personalization remains a significant challenge. Existing approaches often treat user preferences as static or merely time-varying traits, overlooking the dynamic nature of human behavior: preferences can shift, and even conflict, depending on context. To address this limitation, we propose a fine-grained taxonomy to differentiate between stable preferences, which are context-agnostic, and situational preferences, which are contextdependent. Building on this taxonomy, we introduce S2Pref, a new dataset of 10k rigorously constructed entries. Each entry is grounded in a multi-turn dialogue that implicitly manifests either a stable or a situational preference, as defined by our hierarchical taxonomy. We further design three complementary evaluation tasks to benchmark LLMs on their ability to prioritize contextual signals, proactively resolve ambiguity, and efficiently infer user preferences. Our dataset and diagnostic tasks provide a practical testbed for advancing dynamic, context-aware personalization in conversational agents.
问 Lune
几分钟读透这篇 Paper,不用再花一下午。
Lune 能读完全文,也能读引用它的顶会 Paper,讲清它的结论、证据和局限,每一点都注明出自哪篇 Paper。不用硬啃,也不靠猜。
脉络
它引用的 Paper12
- LoRA: Low-Rank Adaptation of Large Language ModelsEdward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu 等ICLR 2022 · 18,833 次引用
- Aligning to Thousands of Preferences via System Message GeneralizationSeongyun Lee, Sue Hyun Park, Seungone Kim, Minjoon SeoNeurIPS 2024 · 102 次引用
- Cue-CoT: Chain-of-thought Prompting for Responding to In-depth Dialogue Questions with LLMsHongru Wang, Rui Wang, Fei Mi, Yang Deng 等EMNLP Findings 2023 · 38 次引用
- Enhancing Personalized Multi-Turn Dialogue with Curiosity RewardYanming Wan, Jiaxing Wu, Marwa Abdulhai, Lior Shani 等NeurIPS 2025 · 32 次引用
- Personalized LoRA for Human-Centered Text UnderstandingYou Zhang, Jin Wang, Liang-Chih Yu, Dan Xu 等AAAI 2024 · 22 次引用
相关 Paper
- Do LLMs Recognize Your Preferences? Evaluating Personalized Preference Following in LLMsSiyan Zhao, Mingyi Hong, Yang Liu, Devamanyu Hazarika 等ICLR 2025
- Towards Proactive Personalization through Profile Customization for Individual Users in DialoguesXiaotian Zhang, Yuan Wang, Ruizhe Chen, Zeya Wang 等ACL Findings 2026
- PersonaLens: A Benchmark for Personalization Evaluation in Conversational AI AssistantsZheng Zhao, Clara Vania, Subhradeep Kayal, Naila Khan 等ACL Findings 2025 · 9 次引用
- Persona2Web: Benchmarking Personalized Web Agents for Contextual Reasoning with User HistorySerin Kim, Sangam Lee, Dongha LeeICML 2026
- A Textual Dataset for Situated Proactive Response SelectionNaoki Otani, Jun Araki, HyeongSik Kim, Eduard H. HovyACL 2023 · 1 次引用
