Article

Post Hoc Explanations of Language Models Can Improve Language Models

2023-06-05

Abstract excerpt

<title>Abstract</title> <p>Large Language Models (LLMs) have demonstrated remarkable capabilities in performing complex tasks. Moreover, recent research has shown that incorporating human-annotated rationales (e.g., Chain-of-Thought prompting) during in-context learning can significantly enhance the performance of these models, particularly on tasks that require reasoning capabilities. However, incorporating such...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 88e662db-4367-5c4e-aaff-76a8901f7f70
DOI: 10.21203/rs.3.rs-3006112/v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Post Hoc Explanations of Language Models Can Improve Language ModelsDOI 10.21203/rs.3.rs-3006112/v1Read

Context-Grounded Factuality Enhancement in LLM Responses via Multi-Stage Critique and RefinementSemantic proximity Read

Exploring Explainability in Large Language ModelsSemantic proximity Read

Reasoning Distillation by Prompt OptimizationSemantic proximity Read

Explainable Automatic Evaluation: Interpretable Decision-Making in Large Language Model AutoratersSemantic proximity Read

iRAT: Replanning and Controlled Retrieval for Robust LLM ReasoningSemantic proximity Read

Mind the Gap: From Plausible to Valid Self-Explanations in Large Language ModelsSemantic proximity Read

Towards Explainable Language Reasoning via Multi-Modal Knowledge GraphsSemantic proximity Read

Anchoring Bias in Large Language Models: An Experimental StudySemantic proximity Read

Beyond Words: The Evolution of Large Language Models in Context-AwareSemantic proximity Read

Dynamic Probabilistic Contextual Realignment in Transformer-Based Large Language Models for Semantic ConsistencySemantic proximity Read

iRAT: Improved Retrieval-Augmented Thinking for Context-Aware Replanning-Based ReasoningSemantic proximity Read

Reasoning in Large Language Models: From Chain-of-Thought to Massively Decomposed Agentic ProcessesSemantic proximity Read