# Separate the Wheat from the Chaff: Model Deficiency Unlearning via Parameter-Efficient Module Operation

arXiv: https://arxiv.org/abs/2308.08090 · HTML: https://mlsanity.com/paper/2308.08090/

## Key facts

- Cited by 33 papers in the map (data through 14 Oct 2026).
- Placed in Machine unlearning, one of 12 directions in LLM safety and security.
- Builds on 41 of its 55 references that are in the map.
- First posted on arXiv 16 Aug 2023.

## Placed in

- LLM safety and security / [Machine unlearning](https://mlsanity.com/safety/machine-unlearning/)

## Builds on (most cited first, 30 of 41)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [Survey of Hallucination in Natural Language Generation](https://mlsanity.com/paper/2202.03629/) (2022)
- [Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them](https://mlsanity.com/paper/2210.09261/) (2022)
- [Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time](https://mlsanity.com/paper/2203.05482/) (2022)
- [Inference-Time Intervention: Eliciting Truthful Answers from a Language Model](https://mlsanity.com/paper/2306.03341/) (2023)
- [WizardLM: Empowering large pre-trained language models to follow complex instructions](https://mlsanity.com/paper/2304.12244/) (2023)
- [Towards a Unified View of Parameter-Efficient Transfer Learning](https://mlsanity.com/paper/2110.04366/) (2021)
- [Instruction Tuning with GPT-4](https://mlsanity.com/paper/2304.03277/) (2023)
- [Merging Models with Fisher-Weighted Averaging](https://mlsanity.com/paper/2111.09832/) (2021)
- [Editing Factual Knowledge in Language Models](https://mlsanity.com/paper/2104.08164/) (2021)
- [Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Space](https://mlsanity.com/paper/2203.14680/) (2022)
- [Neural Text Generation with Unlikelihood Training](https://mlsanity.com/paper/1908.04319/) (2019)
- [Fast Model Editing at Scale](https://mlsanity.com/paper/2110.11309/) (2021)
- [Memory-Based Model Editing at Scale](https://mlsanity.com/paper/2206.06520/) (2022)
- [DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Experts](https://mlsanity.com/paper/2105.03023/) (2021)
- [Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task](https://mlsanity.com/paper/2210.13382/) (2022)
- [How Far Can Camels Go? Exploring the State of Instruction Tuning on Open Resources](https://mlsanity.com/paper/2306.04751/) (2023)
- [Nuanced Metrics for Measuring Unintended Bias with Real Data for Text Classification](https://mlsanity.com/paper/1903.04561/) (2019)
- [Fine-Grained Human Feedback Gives Better Rewards for Language Model Training](https://mlsanity.com/paper/2306.01693/) (2023)

## Built on by (most cited first, 30 of 33)

- [TOFU: A Task of Fictitious Unlearning for LLMs](https://mlsanity.com/paper/2401.06121/) (2024)
- [Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities](https://mlsanity.com/paper/2408.07666/) (2024)
- [A Comprehensive Study of Knowledge Editing for Large Language Models](https://mlsanity.com/paper/2401.01286/) (2024)
- [Detoxifying Large Language Models via Knowledge Editing](https://mlsanity.com/paper/2403.14472/) (2024)
- [RWKU: Benchmarking Real-World Knowledge Unlearning for Large Language Models](https://mlsanity.com/paper/2406.10890/) (2024)
- [Knowledge Circuits in Pretrained Transformers](https://mlsanity.com/paper/2405.17969/) (2024)
- [Machine Unlearning in Generative AI: A Survey](https://mlsanity.com/paper/2407.20516/) (2024)
- [Ethos: Rectifying Language Models in Orthogonal Parameter Space](https://mlsanity.com/paper/2403.08994/) (2024)
- [Disperse-Then-Merge: Pushing the Limits of Instruction Tuning via Alignment Tax Reduction](https://mlsanity.com/paper/2405.13432/) (2024)
- [In-Context Learning State Vector with Inner and Momentum Optimization](https://mlsanity.com/paper/2404.11225/) (2024)
- [SEUF: Is Unlearning One Expert Enough for Mixture-of-Experts LLMs?](https://mlsanity.com/paper/2411.18797/) (2024)
- [CoME: An Unlearning-based Approach to Conflict-free Model Editing](https://mlsanity.com/paper/2502.15826/) (2025)
- [Cross-Modal Unlearning via Influential Neuron Path Editing in Multimodal Large Language Models](https://mlsanity.com/paper/2511.06793/) (2025)
- [Improve Decoding Factuality by Token-wise Cross Layer Entropy of Large Language Models](https://mlsanity.com/paper/2502.03199/) (2025)
- [ExAnte: A Benchmark for Ex-Ante Inference in Large Language Models](https://mlsanity.com/paper/2505.19533/) (2025)
- [Erasing Without Remembering: Implicit Knowledge Forgetting in Large Language Models](https://mlsanity.com/paper/2502.19982/) (2025)
- [Adaptive Detoxification: Safeguarding General Capabilities of LLMs through Toxicity-Aware Knowledge Editing](https://mlsanity.com/paper/2505.22298/) (2025)
- [Generative Model Unlearning: A Survey through Target Events, Unlearning Operators, and Evaluation Protocols](https://mlsanity.com/paper/2507.19894/) (2025)
- [A Survey on Unlearning in Large Language Models](https://mlsanity.com/paper/2510.25117/) (2025)
- [DEM: Distribution Edited Model for Training with Mixed Data Distributions](https://mlsanity.com/paper/2406.15570/) (2024)
- [CKnowEdit: A New Chinese Knowledge Editing Dataset for Linguistics, Facts, and Logic Error Correction in LLMs](https://mlsanity.com/paper/2409.05806/) (2024)
- [CAP: Controllable Alignment Prompting for Unlearning in LLMs](https://mlsanity.com/paper/2604.21251/) (2026)
- [Optimal Brain Iterative Merging: Mitigating Interference in LLM Merging](https://mlsanity.com/paper/2502.12217/) (2025)
- [Reveal and Release: Iterative LLM Unlearning with Self-generated Data](https://mlsanity.com/paper/2509.14624/) (2025)
- [MUC: Machine Unlearning for Contrastive Learning with Black-box Evaluation](https://mlsanity.com/paper/2406.03603/) (2024)
- [Inner-Probe: Discovering Copyright-related Data Generation in LLM Architecture](https://mlsanity.com/paper/2410.04454/) (2024)
- [Task Vector Bases: A Unified and Scalable Framework for Compressed Task Arithmetic](https://mlsanity.com/paper/2502.01015/) (2025)
- [Fine-Grained Detoxification via Instance-Level Prefixes for Large Language Models](https://mlsanity.com/paper/2402.15202/) (2024)
- [PRUNE: A Patching Based Repair Framework for Certifiable Unlearning of Neural Networks](https://mlsanity.com/paper/2505.06520/) (2025)
- [Lifting Data-Tracing Machine Unlearning to Knowledge-Tracing for Foundation Models](https://mlsanity.com/paper/2506.11253/) (2025)

## Abstract (arXiv)

Large language models (LLMs) have been widely used in various applications but are known to suffer from issues related to untruthfulness and toxicity. While parameter-efficient modules (PEMs) have demonstrated their effectiveness in equipping models with new skills, leveraging PEMs for deficiency unlearning remains underexplored. In this work, we propose a PEMs operation approach, namely Extraction-before-Subtraction (Ext-Sub), to enhance the truthfulness and detoxification of LLMs through the integration of ``expert'' PEM and ``anti-expert'' PEM. Remarkably, even anti-expert PEM possess valuable capabilities due to their proficiency in generating fabricated content, which necessitates language modeling and logical narrative competence. Rather than merely negating the parameters, our approach involves extracting and eliminating solely the deficiency capability within anti-expert PEM while preserving the general capabilities. To evaluate the effectiveness of our approach in terms of truthfulness and detoxification, we conduct extensive experiments on LLMs, encompassing additional abilities such as language modeling and mathematical reasoning. Our empirical results demonstrate that our approach effectively improves truthfulness and detoxification, while largely preserving the fundamental abilities of LLMs.