paper-with-me

Papers

Aligning Large Language Models with Searcher Preferences

2026-03-11 · Wei Wu, Peilun Zhou, Liyi Chen, Qimeng Wang, Chengqiang Lu, Yan Gao, Yi Wu, Yao Hu, Hui Xiong arxiv

The paradigm shift from item-centric ranking to answer-centric synthesis is redefining the role of search engines. While recent industrial progress has applied generative techniques to closed-set item ranking in e-commerce, research and deployment of open-ended generative search on large content platforms remain limited. This setting introduces challenges, including robustness to noisy retrieval, non-negotiable safety guarantees, and alignment with diverse user needs. In this work, we introduce SearchLLM, the first large language model (LLM) for open-ended generative search. We design a hierarchical, multi-dimensional reward system that separates bottom-line constraints, including factual grounding, basic answer quality and format compliance, from behavior optimization objectives that promote robustness to noisy retrieval and alignment with user needs. Concretely, our reward model evaluates responses conditioned on the user query, session history, and retrieved evidence set, combining rule-based checks with human-calibrated LLM judges to produce an interpretable score vector over these dimensions. We introduce a Gated Aggregation Strategy to derive the training reward for optimizing SearchLLM with Group Relative Policy Optimization (GRPO). We deploy SearchLLM in the AI search entry of RedNote. Offline evaluations and online A/B tests show improved generation quality and user engagement, increasing Valid Consumption Rate by 1.03% and reducing Re-search Rate by 2.81%, while upholding strict safety and reliability standards.

📄 PDF Abstract BibTeX arXiv:2603.10473

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Can LLMs Capture Human Preferences?

2023-05-04 · Ali Goli, Amandeep Singh

We explore the viability of Large Language Models (LLMs), specifically OpenAI's GPT-3.5 and GPT-4, in emulating human survey respondents and eliciting preferences, with a focus on intertemporal choices. Leveraging the ex…

Benchmarking

Improving In-context Learning via Bidirectional Alignment

2023-12-28 · Chengwei Qin, Wenhan Xia, Fangkai Jiao, Chen Chen 외

Large language models (LLMs) have shown impressive few-shot generalization on many tasks via in-context learning (ICL). Despite their success in showing such emergent abilities, the scale and complexity of larger models …

In-Context Learning

A Good Plan is Hard to Find: Aligning Models with Preferences is Misaligned with What Helps Users

2025-09-23 · Nishant Balepur, Matthew Shu, Yoo Yeon Sung, Seraphina Goldfarb-Tarrant 외 arxiv

To assist users in complex tasks, LLMs generate plans: step-by-step instructions towards a goal. While alignment methods aim to ensure LLM plans are helpful, they train (RLHF) or evaluate (ChatbotArena) on what users pre…

Question Similarity

Statistical Impossibility and Possibility of Aligning LLMs with Human Preferences: From Condorcet Paradox to Nash Equilibrium

2025-03-14 · Kaizhao Liu, Qi Long, Zhekun Shi, Weijie J. Su 외

Aligning large language models (LLMs) with diverse human preferences is critical for ensuring fairness and informed outcomes when deploying these models for decision-making. In this paper, we seek to uncover fundamental …

Fairness

Aligning Large Language Models with Implicit Preferences from User-Generated Content

2025-06-04 · Zhaoxuan Tan, Zheng Li, Tianyi Liu, Haodong Wang 외

Learning from preference feedback is essential for aligning large language models (LLMs) with human values and improving the quality of generated responses. However, existing preference learning methods rely heavily on c…