# SEAT: Sparse Entity-Aware Tuning for Knowledge Adaptation while Preserving Epistemic Abstention

arXiv: https://arxiv.org/abs/2506.14387 · HTML: https://mlsanity.com/paper/2506.14387/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 32 references that are in the map.
- First posted on arXiv 17 Jun 2025.

## Builds on (most cited first, 26 of 26)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Gradient Episodic Memory for Continual Learning](https://mlsanity.com/paper/1706.08840/) (2017)
- [Representation Engineering: A Top-Down Approach to AI Transparency](https://mlsanity.com/paper/2310.01405/) (2023)
- [Editing Models with Task Arithmetic](https://mlsanity.com/paper/2212.04089/) (2022)
- [Steering Language Models With Activation Engineering](https://mlsanity.com/paper/2308.10248/) (2023)
- [The Linear Representation Hypothesis and the Geometry of Large Language Models](https://mlsanity.com/paper/2311.03658/) (2023)
- [Overcoming catastrophic forgetting with hard attention to the task](https://mlsanity.com/paper/1801.01423/) (2018)
- [An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning](https://mlsanity.com/paper/2308.08747/) (2023)
- [TOFU: A Task of Fictitious Unlearning for LLMs](https://mlsanity.com/paper/2401.06121/) (2024)
- [Does Fine-Tuning LLMs on New Knowledge Encourage Hallucinations?](https://mlsanity.com/paper/2405.05904/) (2024)
- [Large Language Models in Law: A Survey](https://mlsanity.com/paper/2312.03718/) (2023)
- [To Believe or Not to Believe Your LLM](https://mlsanity.com/paper/2406.02543/) (2024)
- [R-Tuning: Instructing Large Language Models to Say `I Don't Know'](https://mlsanity.com/paper/2311.09677/) (2023)
- [Continual Learning with Node-Importance based Adaptive Group Sparse Regularization](https://mlsanity.com/paper/2003.13726/) (2020)
- [Revolutionizing Finance with LLMs: An Overview of Applications and Insights](https://mlsanity.com/paper/2401.11641/) (2024)
- [Alignment for Honesty](https://mlsanity.com/paper/2312.07000/) (2023)
- [A Closer Look at Rehearsal-Free Continual Learning](https://mlsanity.com/paper/2203.17269/) (2022)
- [Calibrating Verbal Uncertainty as a Linear Feature to Reduce Hallucinations](https://mlsanity.com/paper/2503.14477/) (2025)
- [LLM Unlearning via Neural Activation Redirection](https://mlsanity.com/paper/2502.07218/) (2025)
- [A Survey on Medical Large Language Models: Technology, Application, Trustworthiness, and Future Directions](https://mlsanity.com/paper/2406.03712/) (2024)
- [I Don't Know: Explicit Modeling of Uncertainty with an [IDK] Token](https://mlsanity.com/paper/2412.06676/) (2024)
- [Controlled Low-Rank Adaptation with Subspace Regularization for Continued Training on Large Language Models](https://mlsanity.com/paper/2410.16801/) (2024)
- [Why Representation Engineering Works: A Theoretical and Empirical Study in Vision-Language Models](https://mlsanity.com/paper/2503.22720/) (2025)

## Built on by (most cited first, 3 of 3)

- [Hallucination reduction with CASAL: Contrastive Activation Steering For Amortized Learning](https://mlsanity.com/paper/2510.02324/) (2025)
- [I-CALM: Incentivizing Confidence-Aware Abstention for LLM Selective Answering](https://mlsanity.com/paper/2604.03904/) (2026)
- [Supervised Fine-Tuning Needs to Unlock the Potential of Token Priority](https://mlsanity.com/paper/2602.01227/) (2026)

## Abstract (arXiv)

Adapting LLMs with new knowledge is increasingly important, but standard fine-tuning often erodes aligned epistemic abstention: the ability to acknowledge when the model does not know. This failure mode is especially concerning in high-stakes settings, where abstention is a critical safeguard against hallucination. We present SEAT, a preventive fine-tuning method that preserves epistemic abstention while maintaining strong knowledge acquisition. SEAT combines sparse tuning, which constrains global activation drift, with entity-perturbed KL regularization, which sharpens local epistemic boundaries and prevents spillover to neighboring knowledge. Crucially, SEAT requires no alignment data, explicit boundary probing, or post-hoc re-alignment, making it attractive for lightweight and privacy-sensitive adaptation. Across models and datasets, SEAT improves human-evaluated abstention on unknown queries by 18%-101% over the strongest baseline while retaining near-perfect target knowledge acquisition, and produces coherent, context-aware abstentions after tuning. Further analyses show that both components are essential, that SEAT more cleanly separates known from unknown queries in representation space, and that it preserves downstream utility. These results identify preservation of epistemic abstention as a core objective for safe knowledge adaptation.