Tell Me What To Learn: Generalizing Neural Memory to be Controllable in Natural Language
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908862890639360 |
|---|---|
| author | Bennett, Max S. Zollo, Thomas P. Zemel, Richard |
| author_facet | Bennett, Max S. Zollo, Thomas P. Zemel, Richard |
| contents | Modern machine learning models are deployed in diverse, non-stationary environments where they must continually adapt to new tasks and evolving knowledge. Continual fine-tuning and in-context learning are costly and brittle, whereas neural memory methods promise lightweight updates with minimal forgetting. However, existing neural memory models typically assume a single fixed objective and homogeneous information streams, leaving users with no control over what the model remembers or ignores over time. To address this challenge, we propose a generalized neural memory system that performs flexible updates based on learning instructions specified in natural language. Our approach enables adaptive agents to learn selectively from heterogeneous information sources, supporting settings, such as healthcare and customer service, where fixed-objective memory updates are insufficient. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_23201 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Tell Me What To Learn: Generalizing Neural Memory to be Controllable in Natural Language Bennett, Max S. Zollo, Thomas P. Zemel, Richard Machine Learning Modern machine learning models are deployed in diverse, non-stationary environments where they must continually adapt to new tasks and evolving knowledge. Continual fine-tuning and in-context learning are costly and brittle, whereas neural memory methods promise lightweight updates with minimal forgetting. However, existing neural memory models typically assume a single fixed objective and homogeneous information streams, leaving users with no control over what the model remembers or ignores over time. To address this challenge, we propose a generalized neural memory system that performs flexible updates based on learning instructions specified in natural language. Our approach enables adaptive agents to learn selectively from heterogeneous information sources, supporting settings, such as healthcare and customer service, where fixed-objective memory updates are insufficient. |
| title | Tell Me What To Learn: Generalizing Neural Memory to be Controllable in Natural Language |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2602.23201 |