On the Query Complexity of Verifier-Assisted Language Generation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913880178950144 |
|---|---|
| author | Botta, Edoardo Li, Yuchen Mehta, Aashay Ash, Jordan T. Zhang, Cyril Risteski, Andrej |
| author_facet | Botta, Edoardo Li, Yuchen Mehta, Aashay Ash, Jordan T. Zhang, Cyril Risteski, Andrej |
| contents | Recently, a plethora of works have proposed inference-time algorithms (e.g. best-of-n), which incorporate verifiers to assist the generation process. Their quality-efficiency trade-offs have been empirically benchmarked on a variety of constrained generation tasks, but the algorithmic design landscape is still largely poorly understood. In this paper, we develop a mathematical framework for reasoning about constrained generation using a pre-trained language model generator oracle and a process verifier--which can decide whether a prefix can be extended to a string which satisfies the constraints of choice. We show that even in very simple settings, access to a verifier can render an intractable problem (information-theoretically or computationally) to a tractable one. In fact, we show even simple algorithms, like tokenwise rejection sampling, can enjoy significant benefits from access to a verifier. Empirically, we show that a natural modification of tokenwise rejection sampling, in which the sampler is allowed to "backtrack" (i.e., erase the final few generated tokens) has robust and substantive benefits over natural baselines (e.g. (blockwise) rejection sampling, nucleus sampling)--both in terms of computational efficiency, accuracy and diversity. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_12123 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | On the Query Complexity of Verifier-Assisted Language Generation Botta, Edoardo Li, Yuchen Mehta, Aashay Ash, Jordan T. Zhang, Cyril Risteski, Andrej Computation and Language Machine Learning Recently, a plethora of works have proposed inference-time algorithms (e.g. best-of-n), which incorporate verifiers to assist the generation process. Their quality-efficiency trade-offs have been empirically benchmarked on a variety of constrained generation tasks, but the algorithmic design landscape is still largely poorly understood. In this paper, we develop a mathematical framework for reasoning about constrained generation using a pre-trained language model generator oracle and a process verifier--which can decide whether a prefix can be extended to a string which satisfies the constraints of choice. We show that even in very simple settings, access to a verifier can render an intractable problem (information-theoretically or computationally) to a tractable one. In fact, we show even simple algorithms, like tokenwise rejection sampling, can enjoy significant benefits from access to a verifier. Empirically, we show that a natural modification of tokenwise rejection sampling, in which the sampler is allowed to "backtrack" (i.e., erase the final few generated tokens) has robust and substantive benefits over natural baselines (e.g. (blockwise) rejection sampling, nucleus sampling)--both in terms of computational efficiency, accuracy and diversity. |
| title | On the Query Complexity of Verifier-Assisted Language Generation |
| topic | Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2502.12123 |