Entity · technique

Semantic Neighbor Mixing

techniqueactivesemantic-neighbor-mixing-5d532786·1 events·first seen Jun 10, 2026

Aliases: Semantic Neighbor Mixing

Co-occurring entities

N-GRPO DeepSeek-R1-Distill-Qwen GRPO (Group Relative Policy Optimization)

More like this (12)

Sparse Mixture-of-Experts When Does Mixing Help? Analyzing Query Embedding Interpolation in Multilingual Dense Retrieval Cascade Spatial-Aware Locality Fusion Supervised Semantic Differential Fast Adaptive Semantic Entropy mixture-density networks When Does Combining Language Models Help? A Co-Failure Ceiling on Routing, Voting, and Mixture-of-Agents Across 67 Frontier Models Construction-Driven Injection: Linguistically-Grounded Edit-Based Code-Mixing Fingerprints for Large Language Models Data Mixture Surgery RegMix MDA (Mixture-Density Ambiguity)Vector Search As Nearest Neighbor Matching: RAG-based Policy Learning in Causal Inference

Recent events (1)

4arXiv · cs.CL·Jun 10, 2026·source ↗

N-GRPO: Semantic Neighbor Mixing for Improved Policy Optimization in LLM Reasoning

A new arXiv preprint introduces N-GRPO, an exploration strategy for the GRPO reinforcement learning framework that improves solution diversity during rollout by mixing embeddings of anchor tokens with their nearest semantic neighbors rather than using token-level sampling or random noise. The method is evaluated on DeepSeek-R1-Distill-Qwen models of various sizes and shows consistent improvements on math reasoning benchmarks plus out-of-distribution generalization. The work targets a known limitation in RLHF-style training: redundant rollout trajectories that reduce effective learning signal.

Evaluation and Benchmarking Alignment and RLHF N-GRPO DeepSeek-R1-Distill-Qwen Semantic Neighbor Mixing +1 more