REVIEW 5 cited by
Learning to Compress Prompts with Gist Tokens
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
Prompting is the primary way to utilize the multitask capabilities of language models (LMs), but prompts occupy valuable space in the input context window, and repeatedly encoding the same prompt is computationally inefficient. Finetuning and distillation methods allow for specialization of LMs without prompting, but require retraining the model for each task. To avoid this trade-off entirely, we present gisting, which trains an LM to compress prompts into smaller sets of "gist" tokens which can be cached and reused for compute efficiency. Gist models can be trained with no additional cost over standard instruction finetuning by simply modifying Transformer attention masks to encourage prompt compression. On decoder (LLaMA-7B) and encoder-decoder (FLAN-T5-XXL) LMs, gisting enables up to 26x compression of prompts, resulting in up to 40% FLOPs reductions, 4.2% wall time speedups, and storage savings, all with minimal loss in output quality.
Forward citations
Cited by 5 Pith papers
-
What to Keep, What to Forget: A Rate--Distortion View of Memory Compaction in LLMs and Agents
KV-cache eviction, prompt compression, recurrent state bounding, and agent memory consolidation are unified as one rate-distortion problem with a shared lower bound, shared failure mode, and transferable mechanisms.
-
ARC-Encoder: learning compressed text representations for large language models
ARC-Encoder pools queries in an encoder's last attention layer to produce compressed continuous representations that a frozen decoder consumes as token embeddings.
-
GEM: Empowering LLM for both Embedding Generation and Language Understanding
GEM fine-tunes decoder-only LLMs with bottleneck special tokens and a mixed next-token prediction and contrastive objective, giving them text-embedding ability with only a modest MMLU drop.
-
Token-Operations-Oriented Inference Optimization Techniques for Large Models
The paper introduces a four-layer technical architecture for token-operations-oriented inference optimization in large models and reviews key technologies and industry status at each layer.
-
Breaking Thought Patterns: A Multi-Dimensional Reasoning Framework for LLMs
LADDER, a proposed mix of chain-of-thought prompting, mixture-of-experts layers, and linear projections, reportedly improves LLM creativity and diversity, but the evidence is thin and partly contradictory.
Discussion (0). Continue with ORCID to comment.