Unlearners Can Lie: Evaluating and Improving Honesty in LLM Unlearning

• URL: http://arxiv.org/abs/2605.08765v1
• Date: Sat, 09 May 2026 07:50:27 GMT
• Title: Unlearners Can Lie: Evaluating and Improving Honesty in LLM Unlearning
• Abstract summary: Unlearning in large language models (LLMs) aims to remove harmful training data while preserving overall utility.<n>Existing methods often hallucinate, generate abnormal token sequences, or behave inconsistently, raising safety and trust concerns.<n>We propose a formal definition of unlearning honesty, which includes preserving both utility and honesty on retained knowledge.
• Score: 19.83087496179494
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Unlearning in large language models (LLMs) aims to remove harmful training data while preserving overall utility. However, we find that existing methods often hallucinate, generate abnormal token sequences, or behave inconsistently, raising safety and trust concerns. According to prior literature on LLM honesty, such behaviors are often associated with dishonesty. This motivates us to investigate the notion of honesty in the context of model unlearning. We propose a formal definition of unlearning honesty, which includes: (1) preserving both utility and honesty on retained knowledge, and (2) ensuring effective forgetting while encouraging the model to acknowledge its limitations and respond consistently to questions related to forgotten knowledge. To systematically evaluate the honesty of unlearning, we introduce a suite of metrics that cover utility, honesty on the retained set, effectiveness of forgetting, rejection rate and refusal stability in Q&A and MCQ settings. Evaluating 9 methods across 3 mainstream families shows that all current methods fail to meet these standards. After experimental and theoretical analyses, we present ReVa, a representation-alignment procedure that fine-tunes feature-randomized unlearned models to better acknowledge forgotten knowledge. On Q&A tasks from the forget set, ReVa achieves the highest rejection rate after two rounds of interaction, nearly doubling the performance of the second-best method. Remarkably, It also improves honesty on the retained set. We release our data and code at https://github.com/renjiegu.

Related papers

• Forget Narrowly, Retain Broadly: Unlearning as an Asymmetric Generalization Problem [16.147107064302435]
  We develop a protocol and training corpus that captures forget-retain structure for real-world factual domains.<n>We introduce JensUn++, an unlearning algorithm that achieves the best forget-retain utility trade-off across three LLMs.
  arXiv  Detail & Related papers  (2026-07-10T09:31:29Z)
• Distinguishable Deletion: Unifying Knowledge Erasure and Refusal for Large Language Model Unlearning [58.725080160369494]
  Distinguishable Deletion ($mathrmD2$) is a paradigm that restricts the response distribution in the latent representation rather than specific tokens.<n>We introduce an energy index that quantifies the presence of knowledge and the separation between unlearned and retained content.<n>Experiments demonstrate that EUA significantly outperforms previous methods, indicating the superiority of $mathrmD2$.
  arXiv  Detail & Related papers  (2026-05-16T03:15:35Z)
• SHRED: Retain-Set-Free Unlearning via Self-Distillation with Logit Demotion [39.17638540496959]
  SHRED (Self-distillation via High-surprisal-only Retain-set-free Entropy Demotion) is a retain-set-free unlearning method built on a key insight.<n>High-information tokens concentrate the model's memorized knowledge, while low-information tokens reflect general language competence.<n> SHRED is robust against relearning attacks and membership-inference attacks, and it maintains stable utility even after many sequential unlearning runs.
  arXiv  Detail & Related papers  (2026-05-08T09:25:18Z)
• REBEL: Hidden Knowledge Recovery via Evolutionary-Based Evaluation Loop [11.291998503454854]
  Machine unlearning for LLMs aims to remove sensitive or copyrighted data from trained models.<n>Standard evaluation metrics rely on benign queries that often mistake superficial information suppression for genuine knowledge removal.<n>We introduce REBEL, an evolutionary approach for adversarial prompt generation designed to probe whether unlearned data can still be recovered.
  arXiv  Detail & Related papers  (2026-02-05T22:54:56Z)
• Leak@$k$: Unlearning Does Not Make LLMs Forget Under Probabilistic Decoding [18.830386174815583]
  We show that textitalmost all existing unlearning methods fail to achieve true forgetting in practice.<n>We introduce textttleak@$k$, a new meta-evaluation metric that quantifies the likelihood of forgotten knowledge reappearing.
  arXiv  Detail & Related papers  (2025-11-07T02:30:05Z)
• Train for Truth, Keep the Skills: Binary Retrieval-Augmented Reward Mitigates Hallucinations [103.16279860448874]
  We propose an online reinforcement learning method using a novel binary retrieval-augmented reward (RAR)<n>For open-ended generation, binary RAR achieves a 39.3% reduction in hallucination rates.<n>In short-form question answering, the model learns abstention, strategically outputting "I don't know" when faced with insufficient parametric knowledge.
  arXiv  Detail & Related papers  (2025-10-20T16:45:43Z)
• Forget to Know, Remember to Use: Context-Aware Unlearning for Large Language Models [17.249936460923045]
  Large language models may encode sensitive information or outdated knowledge that needs to be removed.<n>Unlearning is an efficient alternative to full retraining, aiming to remove specific knowledge while preserving overall model utility.
  arXiv  Detail & Related papers  (2025-10-20T15:03:45Z)
• Unlearning That Lasts: Utility-Preserving, Robust, and Almost Irreversible Forgetting in LLMs [31.768387661474904]
  Unlearning in large language models (LLMs) involves precisely removing specific information from a pre-trained model.<n>This is crucial to ensure safety of LLMs by deleting private data or harmful knowledge acquired during pre-training.<n>We introduce JensUn, where we leverage the Jensen-Shannon Divergence as the training objective for both forget and retain sets.<n>In extensive experiments, JensUn achieves better forget-utility trade-off than competing methods, and even demonstrates strong resilience to benign relearning.
  arXiv  Detail & Related papers  (2025-09-02T20:38:53Z)
• Existing Large Language Model Unlearning Evaluations Are Inconclusive [105.55899615056573]
  We show that some evaluations introduce substantial new information into the model, potentially masking true unlearning performance.<n>We demonstrate that evaluation outcomes vary significantly across tasks, undermining the generalizability of current evaluation routines.<n>We propose two principles for future unlearning evaluations: minimal information injection and downstream task awareness.
  arXiv  Detail & Related papers  (2025-05-31T19:43:00Z)
• Unlearning vs. Obfuscation: Are We Truly Removing Knowledge? [20.952703558942453]
  We formally distinguish unlearning from obfuscation and introduce a probing-based evaluation framework.<n>We propose DF-MCQ, a novel unlearning method that flattens the model predictive distribution over automatically generated multiple-choice questions.<n> Experimental results demonstrate that DF-MCQ achieves unlearning with over 90% refusal rate and a random choice-level uncertainty.
  arXiv  Detail & Related papers  (2025-05-05T14:21:08Z)
• Erasing Without Remembering: Implicit Knowledge Forgetting in Large Language Models [81.62767292169225]
  We investigate knowledge forgetting in large language models with a focus on its generalisation.<n>We propose PerMU, a novel probability perturbation-based unlearning paradigm.<n>Experiments are conducted on a diverse range of datasets, including TOFU, Harry Potter, ZsRE, WMDP, and MUSE.
  arXiv  Detail & Related papers  (2025-02-27T11:03:33Z)
• Towards Effective Evaluations and Comparisons for LLM Unlearning Methods [97.2995389188179]
  This paper seeks to refine the evaluation of machine unlearning for large language models.<n>It addresses two key challenges -- the robustness of evaluation metrics and the trade-offs between competing goals.
  arXiv  Detail & Related papers  (2024-06-13T14:41:00Z)
• Alignment for Honesty [105.72465407518325]
  Recent research has made significant strides in aligning large language models (LLMs) with helpfulness and harmlessness. In this paper, we argue for the importance of alignment for emphhonesty, ensuring that LLMs proactively refuse to answer questions when they lack knowledge. We address these challenges by first establishing a precise problem definition and defining honesty'' inspired by the Analects of Confucius.
  arXiv  Detail & Related papers  (2023-12-12T06:10:42Z)
• Improving the Reliability of Large Language Models by Leveraging Uncertainty-Aware In-Context Learning [76.98542249776257]
  Large-scale language models often face the challenge of "hallucination" We introduce an uncertainty-aware in-context learning framework to empower the model to enhance or reject its output in response to uncertainty.
  arXiv  Detail & Related papers  (2023-10-07T12:06:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.