DYCP: Dynamic Context Pruning for Long-Form Dialogue with LLMs
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915925631959040 |
|---|---|
| author | Choi, Nayoung Zhang, Jonathan Choi, Jinho D. |
| author_facet | Choi, Nayoung Zhang, Jonathan Choi, Jinho D. |
| contents | Large Language Models (LLMs) increasingly operate over long-form dialogues with frequent topic shifts. While recent LLMs support extended context windows, efficient management of dialogue history in practice is needed due to inference cost and latency constraints. We present DyCP, a lightweight context management method implemented outside the LLM that dynamically identifies and retrieves relevant dialogue segments conditioned on the current turn, without offline memory construction. DyCP manages dialogue context while preserving the sequential nature of dialogue without predefined topic boundaries, enabling adaptive and efficient context selection. Across three long-form dialogue benchmarks-LoCoMo, MT-Bench+, and SCM4LLMs-and multiple LLM backends, DyCP achieves competitive answer quality in downstream generation, with more selective context usage and improved inference efficiency. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_07994 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | DYCP: Dynamic Context Pruning for Long-Form Dialogue with LLMs Choi, Nayoung Zhang, Jonathan Choi, Jinho D. Computation and Language Artificial Intelligence Large Language Models (LLMs) increasingly operate over long-form dialogues with frequent topic shifts. While recent LLMs support extended context windows, efficient management of dialogue history in practice is needed due to inference cost and latency constraints. We present DyCP, a lightweight context management method implemented outside the LLM that dynamically identifies and retrieves relevant dialogue segments conditioned on the current turn, without offline memory construction. DyCP manages dialogue context while preserving the sequential nature of dialogue without predefined topic boundaries, enabling adaptive and efficient context selection. Across three long-form dialogue benchmarks-LoCoMo, MT-Bench+, and SCM4LLMs-and multiple LLM backends, DyCP achieves competitive answer quality in downstream generation, with more selective context usage and improved inference efficiency. |
| title | DYCP: Dynamic Context Pruning for Long-Form Dialogue with LLMs |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2601.07994 |