Research map / Large language models / Instruction and fine-tuning

Boosting Resilience of Large Language Models through Causality-Driven Robust Optimization

NeurIPS 2025 · Large language models › Instruction and fine-tuning · approach: Efficient LLM fine-tuning systems · 0 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes a causality-driven robust optimization approach to improve LLM resilience against spurious correlations and hallucination, targeting parameter-efficient, specific fixes instead of full fine-tuning or post-processing.

Problem

LLMs are plagued by spurious correlations and hallucinated content; existing resilience methods either fine-tune all parameters indiscriminately (parameter-inefficient, unspecific) or rely on post-processing.

Approach

Uses causal reasoning to guide robust optimization so that only targeted parameters are adjusted to improve resilience, rather than indiscriminate full-parameter fine-tuning or post-hoc correction. Details beyond the abstract are not available.

Closest papers by meaning

• Rethinking the Development of Large Language Models from the Causal Perspective: A Legal Text Prediction Case Study (AAAI 2024 · similarity 0.90)
• Boosting Multi-Domain Fine-Tuning of Large Language Models through Evolving Interactions between Samples (ICML 2025 · similarity 0.90)
• COPO: Causal-Oriented Policy Optimization for Hallucinations of MLLMs (CVPR 2026 · similarity 0.89)
• Remarkable Robustness of LLMs: Stages of Inference? (NeurIPS 2025 · similarity 0.89)
• Large Language Models to Enhance Bayesian Optimization (ICLR 2024 · similarity 0.89)
• Model Fusion through Bayesian Optimization in Language Model Fine-Tuning (NeurIPS 2024 · similarity 0.88)