# Axis-LoRA: Probing and Adapting Embedding Models for Personal-Memory Retrieval

**Authors:** Dohoon Kim, Junho Park, Hyunwoong Bae, Seyoon Kim, Taesup Moon  
**Lab:** Seoul National University · **Published:** 5 Nov 2026  
**Links:** [arXiv](https://arxiv.org/abs/2611.07820) · [PDF](https://arxiv.org/pdf/2611.07820) · [Code](https://github.com/dohoonkim-ai/axis-lora) · [This page](https://omen-bit.github.io/ai-paper-daily/paper/2611.07820.html)

## Abstract

As LLMs are increasingly asked questions about a user's personal experiences, retrieval must distinguish memories by time, place, person, and event. Current personal-memory pipelines rely on frozen dense embedding models to embed memories for retrieval, but we find that these models do not capture the four axes well. Swapping a memory's date or place barely shifts its embedding, and a trained projection on top of the frozen embedding does not recover the missing signal. The problem lives inside the model, where each axis is encoded by a distinct attention-head pattern. Guided by these findings, we propose Axis-LoRA, a per-axis adapter that places four LoRA branches inside the embedding model and combines them via a per-query gate. Across three standard embedding models evaluated on LongMemEval, ATM-Bench, and LoCoMo, Axis-LoRA improves 4-benchmark mean R@10 by $+1.28$ to $+1.56$~pp while training only a small fraction of the base parameters on a small axis-counterfactual training set. Code is available at https://github.com/dohoonkim-ai/axis-lora.

---

Notes written by AI from the paper, numbers copied from the abstract. Check the paper before you rely on them. From AI Papers Daily.