Noise Augmented Fine Tuning for Mitigating Hallucinations in Large Language Models
cs.CL, cs.AI
Submitted: 2025-04-04
Updated: 2025-05-03
DOI: 10.1016/j.neucom.2026.134636
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- NEFTune: Noisy Embeddings Improve Instruction Finetuning
- Noise2Noise: Learning Image Restoration without Clean Data
- HaluEval: A Large-Scale Hallucination Evaluation Benchmark for Large Language Models
- Enhancing Hallucination Detection through Noise Injection
- Decoupled Weight Decay Regularization
- MuSR: Testing the Limits of Chain-of-thought with Multistep Soft Reasoning
- Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them
- Noise Injection Reveals Hidden Capabilities of Sandbagging Language Models
- Taming Sensitive Weights : Noise Perturbation Fine-tuning for Robust LLM Quantization
- Noise-Robust Fine-Tuning of Pretrained Language Models via External Guidance
- BloombergGPT: A Large Language Model for Finance
- SymNoise: Advancing Language Model Fine-tuning with Symmetric Noise
- Instruction-Following Evaluation for Large Language Models
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering