DSPy compiles short declarative programs into LM pipelines that self-optimize and outperform both standard few-shot prompting and expert-written chains on math, retrieval, and QA tasks.
Prompting gpt-3 to be reliable
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
REPLUG improves frozen black-box LMs by prepending LM-supervised retrieved documents, delivering 6.3% better language modeling on GPT-3 and 5.1% better five-shot MMLU on Codex.
SIVR detects LLM hallucinations by learning from token-wise and layer-wise variance patterns in internal hidden states, outperforming baselines with better generalization and less training data.
Survey organizes LLM trustworthiness into seven categories and 29 sub-categories, measures eight sub-categories on popular models, and finds that more aligned models generally score higher but with varying effectiveness.
A survey that compiles and taxonomizes more than 32 existing hallucination mitigation techniques for LLMs while analyzing their challenges and limitations.
A survey paper providing an overview of Large Language Models, their background, and recent advances in the field.
citing papers explorer
-
DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines
DSPy compiles short declarative programs into LM pipelines that self-optimize and outperform both standard few-shot prompting and expert-written chains on math, retrieval, and QA tasks.
-
REPLUG: Retrieval-Augmented Black-Box Language Models
REPLUG improves frozen black-box LMs by prepending LM-supervised retrieved documents, delivering 6.3% better language modeling on GPT-3 and 5.1% better five-shot MMLU on Codex.
-
Learning Uncertainty from Sequential Internal Dispersion in Large Language Models
SIVR detects LLM hallucinations by learning from token-wise and layer-wise variance patterns in internal hidden states, outperforming baselines with better generalization and less training data.
-
Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment
Survey organizes LLM trustworthiness into seven categories and 29 sub-categories, measures eight sub-categories on popular models, and finds that more aligned models generally score higher but with varying effectiveness.
-
A Comprehensive Survey of Hallucination Mitigation Techniques in Large Language Models
A survey that compiles and taxonomizes more than 32 existing hallucination mitigation techniques for LLMs while analyzing their challenges and limitations.
-
A Comprehensive Overview of Large Language Models
A survey paper providing an overview of Large Language Models, their background, and recent advances in the field.