ResoFilter keeps fine-tuning examples that produce small parameter updates in the last layers, matching full-data fine-tuning on GSM8k with 50% of the math data.
Scalable Model Editing via Customized Expert Networks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Addressing the issues of hallucinations and outdated knowledge in large language models is critical for their reliable application. Model Editing presents a promising avenue for mitigating these challenges in a cost-effective manner. However, existing methods often suffer from unsatisfactory generalization and unintended effects on non-edited samples. To overcome these limitations, we introduce a novel approach: Scalable Model Editing via Customized Expert Networks (SCEN), which is a two-stage continuous training paradigm. Specifically, in the first stage, we train lightweight expert networks individually for each piece of knowledge that needs to be updated. Subsequently, we train a corresponding indexing neuron for each expert to control the activation state of that expert. We conducted a series of experiments on the ZsRE and Hallucination benchmarks by tuning the advanced open-source LLM, Llama2, achieving state-of-the-art results compared to current mainstream methods. Our code is available at https://github.com/TAL-auroraX/SCEN.
fields
cs.CL 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
ResoFilter: Fine-grained Synthetic Data Filtering for Large Language Models through Data-Parameter Resonance Analysis
ResoFilter keeps fine-tuning examples that produce small parameter updates in the last layers, matching full-data fine-tuning on GSM8k with 50% of the math data.