GIER: Gap-Driven Self-Refinement for Large Language Models
By: Rinku Dewri
Potential Business Impact:
Makes AI smarter by letting it fix its own mistakes.
We introduce GIER (Gap-driven Iterative Enhancement of Responses), a general framework for improving large language model (LLM) outputs through self-reflection and revision based on conceptual quality criteria. Unlike prompting strategies that rely on demonstrations, examples, or chain-of-thought templates, GIER utilizes natural language descriptions of reasoning gaps, and prompts a model to iteratively critique and refine its own outputs to better satisfy these criteria. Across three reasoning-intensive tasks (SciFact, PrivacyQA, and e-SNLI) and four LLMs (GPT-4.1, GPT-4o Mini, Gemini 1.5 Pro, and Llama 3.3 70B), GIER improves rationale quality, grounding, and reasoning alignment without degrading task accuracy. Our analysis demonstrates that models can not only interpret abstract conceptual gaps but also translate them into concrete reasoning improvements.
Similar Papers
Self-Critique Guided Iterative Reasoning for Multi-hop Question Answering
Computation and Language
Helps computers solve hard problems by thinking step-by-step.
Beyond Fast and Slow: Cognitive-Inspired Elastic Reasoning for Large Language Models
Artificial Intelligence
Helps AI think smarter, faster, and more accurately.
Learning to Refine: Self-Refinement of Parallel Reasoning in LLMs
Machine Learning (CS)
AI learns to fix its own math mistakes.