cs.CLNov 11, 2026

ShadowBench: Exposing Lexical Anchoring and the Illusion of Forgetting in Large Language Models

Authors: Sujan Maharjan, Lu Liu

Organizations: Department of Computer Science North Dakota State University Fargo, ND 58102

Abstract

Large Language Models (LLMs) have emerged as primary interfaces for factual retrieval, yet current evaluation paradigms rely almost exclusively on explicit entity names. In this work, we demonstrate that LLM knowledge is fundamentally lexically anchored: models possess extensive factual information but find it significantly difficult to retrieve without explicit name tokens. To quantify this limitation, we introduce ShadowBench, a rigorously hardened, shortcut-resistant benchmark designed to evaluate Latent Entity Association via a novel Dual-Trait Association (DTA) task. Our evaluation reveals a pervasive "Shadow Gap" across all model scales\unicodex2013\unicode{x2013}up to the frontier models GPT-5.4 and Claude-Sonnet-4.6\unicodex2013\unicode{x2013}where removing lexical anchors causes performance drops of over 20%. Furthermore, we demonstrate that this lexical dependency exposes a critical vulnerability in AI safety. Applying ShadowBench to Machine Unlearning, we find that state-of-the-art algorithms (e.g., Gradient Difference, NPO) achieve only superficial lexical erasure. While unlearned models fail on direct queries, our novel Latent Entity Leakage Rate (LELR) metric reveals that for popular entities, models explicitly reconstruct the "forgotten" entity in their internal reasoning traces in over 74% of cases, utilizing residual shadow knowledge to solve associative tasks. Conversely, for niche entities, models retain high shadow accuracy (60-90%) via implicit attribute correlation despite 0% LELR. Ultimately, ShadowBench indicates that current unlearning paradigms create an "Illusion of Forgetting," demonstrating that existing methods act as superficial output filters and are not yet reliable for achieving true parametric erasure.

Explore similar work

Aug 3, 2026

Exploring and Bridging Knowledge Holes in Unlearned Multimodal Large Language Models

Machine unlearning offers a promising approach to remove unsafe content from Multimodal Large Language Models (MLLMs), yet ensuring the precision of unlearning remains a persistent challenge. One reason is that current MLLM unlearning evaluation paradigms suffer from a critical blind spot: they assess model utility through benchmarks whose representations are distant from the forget set, failing to capture knowledge holes---severe degradation on benign adjacent inputs. To probe knowledge holes in unlearned MLLMs, we construct a benchmark that captures unintended degradation on benign inputs sharing generic patterns with the forget set, and confirm through controlled experiments that they are a systematic consequence of commonly used approaches. Furthermore, to bridge this gap, we propose Selective Protection with Anchored Regularization, which protects generic patterns via anchored activation filtering while reinforcing them through entity-abstracted enhancement. Our experiments on SafeEraser demonstrate that SPAR recovers over 98% of vanilla response quality compared to below 50% for standard baselines---while achieving 0.00% attack success rate and competitive model utility. These results underscore the necessity of more fine-grained evaluation for trustworthy MLLM unlearning.
Mar 11, 2026

The Unlearning Mirage: A Dynamic Framework for Evaluating LLM Unlearning

Unlearning in Large Language Models (LLMs) aims to enhance safety, mitigate biases, and comply with legal mandates, such as the right to be forgotten. However, existing unlearning methods are brittle: minor query modifications, such as multi-hop reasoning and entity aliasing, can recover supposedly forgotten information. As a result, current evaluation metrics often create an illusion of effectiveness, failing to detect these vulnerabilities due to reliance on static, unstructured benchmarks. We propose a dynamic framework that stress tests unlearning robustness using complex structured queries. Our approach first elicits knowledge from the target model (pre-unlearning) and constructs targeted probes, ranging from simple queries to multi-hop chains, allowing precise control over query difficulty. Our experiments show that the framework (1) shows comparable coverage to existing benchmarks by automatically generating semantically equivalent Q&A probes, (2) aligns with prior evaluations, and (3) uncovers new unlearning failures missed by other benchmarks, particularly in multi-hop settings. Furthermore, activation analyses show that single-hop queries typically follow dominant computation pathways, which are more likely to be disrupted by unlearning methods. In contrast, multi-hop queries tend to use alternative pathways that often remain intact, explaining the brittleness of unlearning techniques in multi-hop settings. Our framework enables practical and scalable evaluation of unlearning methods without the need for manual construction of forget test sets, enabling easier adoption for real-world applications. We release the pip package and the code at https://sites.google.com/view/unlearningmirage/home.
Sep 26, 2026

LLM Unlearning Evaluation with TRIAGE

Large language models can memorize private or harmful information, motivating machine unlearning methods that remove targeted knowledge while preserving other capabilities. However, existing evaluations rely primarily on behavioral benchmarks, which assess whether a model appears to forget but provide limited insight into how unlearning changes the model or affects related knowledge. We introduce TRIAGE (Tripartite Representation-internal Introspection for Adjacency Gap Evaluation), a benchmark-agnostic evaluation framework for characterizing these changes. TRIAGE uses diagonal approximations of the Fisher information and Hessian to measure changes in parameter sensitivity and local curvature, and utilizes a Forget / Adjacent-Retain / Generic-Retain partition to quantify an adjacency gap in semantically related knowledge. Based on the magnitude and distribution of these changes, TRIAGE further classifies each algorithm's update as no-op, partially localized, collateral dominant, or globally destructive. Across 12 unlearning methods, four language models, and the WMDP, TOFU, and MUSE benchmarks, we find that methods with similar behavioral forgetting can produce substantially different internal changes and patterns of collateral damage. These signatures also vary across models and benchmarks, indicating that the effects of unlearning are not determined solely by the unlearning algorithm. TRIAGE can be applied alongside existing unlearning benchmarks to complement behavioral evaluation with a model-internal view of how unlearning reshapes the model's parameter space and affects retained knowledge.