REVIEW 2 cited by
Classifiers are Better Experts for Controllable Text Generation
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
This paper proposes a simple method for controllable text generation based on weighting logits with a free-form classifier, namely CAIF sampling. Using an arbitrary text classifier, we adjust a small part of a language model's logits and guide text generation towards or away from classifier prediction. We experimented with toxicity avoidance and sentiment control tasks and showed that the proposed method significantly outperforms recent PPLM, GeDi, and DExperts on PPL and task accuracy metrics based on the external classifier of generated texts. In addition, compared to other approaches, it is easier to implement and tune and has significantly fewer restrictions and requirements.
Forward citations
Cited by 2 Pith papers
-
Controlled LLM Decoding via Discrete Auto-regressive Biasing
DAB biases auto-regressive LLM generation using discrete gradient-based MCMC on an auxiliary token sequence, improving constraint satisfaction with similar fluency and lower per-step cost.
-
Decoupling Task-Solving and Output Formatting in LLM Generation
A decoding-time method that keeps the format in a separate module improves LLM accuracy by 1–6% with guaranteed format compliance on math, judging, and extraction.
Discussion (0). Continue with ORCID to comment.