RECALL: Library-Like Behavior In Language Models is Enhanced by Self-Referencing Causal Cycles
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913661950361600 |
|---|---|
| author | Nwadike, Munachiso Iklassov, Zangir Aremu, Toluwani Hiraoka, Tatsuya Bojkovic, Velibor Heinzerling, Benjamin Alqaubeh, Hilal Takáč, Martin Inui, Kentaro |
| author_facet | Nwadike, Munachiso Iklassov, Zangir Aremu, Toluwani Hiraoka, Tatsuya Bojkovic, Velibor Heinzerling, Benjamin Alqaubeh, Hilal Takáč, Martin Inui, Kentaro |
| contents | We introduce the concept of the self-referencing causal cycle (abbreviated RECALL) - a mechanism that enables large language models (LLMs) to bypass the limitations of unidirectional causality, which underlies a phenomenon known as the reversal curse. When an LLM is prompted with sequential data, it often fails to recall preceding context. For example, when we ask an LLM to recall the line preceding "O say does that star-spangled banner yet wave" in the U.S. National Anthem, it often fails to correctly return "Gave proof through the night that our flag was still there" - this is due to the reversal curse. It occurs because language models such as ChatGPT and Llama generate text based on preceding tokens, requiring facts to be learned and reproduced in a consistent token order. While the reversal curse is often viewed as a limitation, we offer evidence of an alternative view: it is not always an obstacle in practice. We find that RECALL is driven by what we designate as cycle tokens - sequences that connect different parts of the training data, enabling recall of preceding tokens from succeeding ones. Through rigorous probabilistic formalization and controlled experiments, we demonstrate how the cycles they induce influence a model's ability to reproduce information. To facilitate reproducibility, we provide our code and experimental details at https://anonymous.4open.science/r/remember-B0B8/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_13491 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | RECALL: Library-Like Behavior In Language Models is Enhanced by Self-Referencing Causal Cycles Nwadike, Munachiso Iklassov, Zangir Aremu, Toluwani Hiraoka, Tatsuya Bojkovic, Velibor Heinzerling, Benjamin Alqaubeh, Hilal Takáč, Martin Inui, Kentaro Computation and Language Artificial Intelligence We introduce the concept of the self-referencing causal cycle (abbreviated RECALL) - a mechanism that enables large language models (LLMs) to bypass the limitations of unidirectional causality, which underlies a phenomenon known as the reversal curse. When an LLM is prompted with sequential data, it often fails to recall preceding context. For example, when we ask an LLM to recall the line preceding "O say does that star-spangled banner yet wave" in the U.S. National Anthem, it often fails to correctly return "Gave proof through the night that our flag was still there" - this is due to the reversal curse. It occurs because language models such as ChatGPT and Llama generate text based on preceding tokens, requiring facts to be learned and reproduced in a consistent token order. While the reversal curse is often viewed as a limitation, we offer evidence of an alternative view: it is not always an obstacle in practice. We find that RECALL is driven by what we designate as cycle tokens - sequences that connect different parts of the training data, enabling recall of preceding tokens from succeeding ones. Through rigorous probabilistic formalization and controlled experiments, we demonstrate how the cycles they induce influence a model's ability to reproduce information. To facilitate reproducibility, we provide our code and experimental details at https://anonymous.4open.science/r/remember-B0B8/. |
| title | RECALL: Library-Like Behavior In Language Models is Enhanced by Self-Referencing Causal Cycles |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2501.13491 |