We lifted 3 functions out of this paper's own repositories and ran 1 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| rmldj/memory-llm-paper | canonical | 1 of 3 |
| Function | Status | Where it lives |
|---|---|---|
| get_objects_verb_reverse | Ran | rmldj/memory-llm-paper/memory.py code served (permissive licence) · get_code("9d869c81d439bb2f") |
| get_distractor | Not yet run | rmldj/memory-llm-paper/memory.py code served (permissive licence) · get_code("82e666da6a26665e") |
| prepare_test | Not yet run | rmldj/memory-llm-paper/memory.py code served (permissive licence) · get_code("809f7faac8e78322") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Large Language Models (LLMs) are huge artificial neural networks which primarily serve to generate text, but also provide a very sophisticated probabilistic model of language use. Since generating a semantically consistent text requires a form of effective memory, we investigate the memory properties of LLMs and find surprising similarities with key characteristics of human memory. We argue that the human-like memory properties of the Large Language Model do not follow automatically from the LLM architecture but are rather learned from the statistics of the training textual data. These results strongly suggest that the biological features of human memory leave an imprint on the way that we structure our textual narratives.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2311.03839")
get_code_for_paper("2311.03839")
have("2311.03839")
Connect an agent — have() is free.