Multi-Teacher Reasoning Distillation for LLM Recommendation with Self-Exploration
cs.IR, cs.AI
Submitted: 2026-11-02
Updated: 2026-11-02
Terminology
Sources
- LASAR: Latent Adaptive Semantic Aligned Reasoning for Generative Recommendation
- Towards Sample-Efficient and Stable Reinforcement Learning for LLM-based Recommendation
- Reinforced Preference Optimization for Reasoning-Augmented Recommendations
- End-to-end Training for Recommendation with Language-based User Profiles
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Session-based Recommendations with Recurrent Neural Networks
- AdNanny: One Reasoning LLM for All Offline Ads Recommendation Tasks
- SCoTER: Structured Chain-of-Thought Transfer for Enhanced Recommendation
- DiffuReason: Bridging Latent Reasoning and Generative Refinement for Sequential Recommendation
- Towards General Text Embeddings with Multi-stage Contrastive Learning
- Evidence Recomposition and Predictive Context Residualization for Visual Attribution in Multimodal Large Language Models
- GR2: Generative Reasoning Re-ranker
- A Survey of Large Audio Language Models: Generalization, Trustworthiness, and Outlook
- Representation Learning with Contrastive Predictive Coding
- FlexRec: Adapting LLM-based Recommenders for Flexible Needs via Reinforcement Learning
- TokenRec: Learning to Tokenize ID for LLM-based Generative Recommendation
- DeepSeek-Prover-V2: Advancing Formal Mathematical Reasoning via Reinforcement Learning for Subgoal Decomposition
- Towards Reliable Medical LLMs: Benchmarking and Enhancing Confidence Estimation of Large Language Models in Medical Consultation
- SCOReD: Student-Aware CoT Optimization for Recommendation Distillation
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
Related papers
- Revisiting Text Ranking in Deep Research
- GateSID: One Gate to Balance Semantic and Collaborative Signals across the Item Lifecycle
- SAM-D2Q: Aligning Multimodal Doc2Query with Search Demand and Conversion for E-commerce
- GINGER: Spicing Up Graph-Based Vector Search
- Subtraction Gets You More: Gap-Aware Retrieval for Multimodal Multi-Hop QA
- One-Step Retrieval Framework for Real-Time Sponsored Search Ads Using Hierarchical Text Representations