REVIEW 7 cited by
Stay on topic with Classifier-Free Guidance
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
Classifier-Free Guidance (CFG) has recently emerged in text-to-image generation as a lightweight technique to encourage prompt-adherence in generations. In this work, we demonstrate that CFG can be used broadly as an inference-time technique in pure language modeling. We show that CFG (1) improves the performance of Pythia, GPT-2 and LLaMA-family models across an array of tasks: Q\&A, reasoning, code generation, and machine translation, achieving SOTA on LAMBADA with LLaMA-7B over PaLM-540B; (2) brings improvements equivalent to a model with twice the parameter-count; (3) can stack alongside other inference-time methods like Chain-of-Thought and Self-Consistency, yielding further improvements in difficult tasks; (4) can be used to increase the faithfulness and coherence of assistants in challenging form-driven and content-driven prompts: in a human evaluation we show a 75\% preference for GPT4All using CFG over baseline.
Forward citations
Cited by 7 Pith papers
-
CorrSynth -- A Correlated Sampling Method for Diverse Dataset Generation from LLMs
By sampling multiple LLM continuations in parallel with mutual contrast, CorrSynth yields more diverse synthetic classification datasets and higher student accuracy than few-shot generation.
-
Wrong Design Intent Is Worse Than Never Conditioning: A Derangement-Control Diagnosis of Header Conditioning in CAD Program Completion
A wrong design-intent header degrades CAD completion below the no-header baseline, and a derangement-trained control shows the harm comes from the learned header-program mapping.
-
Koel-TTS: Enhancing LLM based Speech Generation with Preference Alignment and Classifier Free Guidance
Koel-TTS combines ASR/SV-based preference alignment (DPO/RPO) with classifier-free guidance to improve zero-shot TTS intelligibility, speaker similarity, and naturalness.
-
Simple Guidance Mechanisms for Discrete Diffusion Models
Uniform-noise discrete diffusion trained with a continuous-time variational bound (UDLM) plus discrete classifier-free and classifier-based guidance improves controllable generation over autoregressive baselines on ge...
-
TinyMusician: On-Device Music Generation with Knowledge Distillation and Mixed Precision Quantization
TinyMusician distills MusicGen and applies hand-picked mixed-precision quantization to make a 1.04 GB on-device music generator, but the headline '93% quality, 55% smaller' claims conflict with the paper's own tables.
-
Uncertainty-Driven Expert Control: Enhancing the Reliability of Medical Vision-Language Models
Expert-CFG combines entropy-based uncertainty selection with classifier-free guidance over expert-highlighted text to refine MedVLM outputs, reporting gains on VQA-RAD, SLAKE, and PathVQA.
-
The Codec Language Model-based Zero-Shot Spontaneous Style TTS System for CoVoC Challenge 2024
A codec language model with delay-pattern decoding, classifier-free guidance, and spontaneous-data fine-tuning achieved the top naturalness score in the CoVoC 2024 challenge.
Discussion (0). Continue with ORCID to comment.