English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Even after fine-tuning and reinforcement learning, large language models(LLMs) can be difficult, if not impossible, to control reliably with promptsalone. We propose a new inference-time approach to enforcing syntactic andsemantic constraints on the outputs of LLMs, called sequential Monte Carlo(SMC) steering. The key idea is to specify language generation tasks asposterior inference problems in a class of discrete probabilistic sequencemodels, and replace standard decoding with sequential Monte Carlo inference.For a computational cost similar to that of beam search, SMC can steer LLMs tosolve diverse tasks, including infilling, generation under syntacticconstraints, and prompt intersection. To facilitate experimentation with SMCsteering, we present a probabilistic programming library, LLaMPPL(https://github.com/probcomp/hfppl), for concisely specifying new generationtasks as language model probabilistic programs, and automating steering ofLLaMA-family Transformers.

Sequential Monte Carlo Steering of Large Language Models using Probabilistic Programs