Challenge: Entity-based QA is a common framework for analyzing non-verbatim memorization, but typically query each entity using a single canonical surface form.
Approach: They propose a dataset that pairs Wikidata factual triples with categorized entity surface forms . they examine surface-conditioned factual memorization and find that prediction outcomes change when only the entity surface form is changed.
Outcome: The proposed dataset shows that large language models memorize factual knowledge when only the subject entity surface form is changed.

Similar Papers

The Model Agreed, But Didn’t Learn: Diagnosing Surface Compliance in Large Language Models (2026.findings-acl)

Copied to clipboard

Challenge: Large Language Models internalize vast world knowledge as parametric memory, yet inherit the staleness and errors of their source corpora.
Approach: They propose a framework that subjects models to discriminative self-assessment under diverse contextual pressures to scrutinize subtle behavioral nuances induced by memory modifications.
Outcome: The proposed framework achieves high benchmarks without overwriting internal beliefs, while recursive modifications accumulate representational residues, triggering cognitive instability and permanently diminishing the reversibility of the model’s memory state.
From Remembering to Metacognition: Do Existing Benchmarks Accurately Evaluate LLMs? (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing benchmark datasets focus on low-level cognitive tasks while providing limited coverage of higher-level reasoning skills.
Approach: They analyze the cognitive depth of popular LLM benchmarks using Bloom’s Taxonomy to evaluate both the cognitive and knowledge dimensions.
Outcome: The results show that incorporating higher-level cognitive instructions into the current instruction fine-tuning process improves model performance.
Facts Fade Fast: Evaluating Memorization of Outdated Medical Knowledge in Large Language Models (2025.findings-emnlp)

Copied to clipboard

Challenge: LLMs encode extensive knowledge within their parameters, but the knowledge in LLM models can become outdated over time.
Approach: They propose two new LLMs that provide outdated medical advice . they compare the models with a set of QA pairs whose verdict changed through time .
Outcome: The proposed models exhibit memorization of outdated knowledge to some extent.
Unveiling Entity-Level Unlearning for Large Language Models: A Comprehensive Analysis (2025.coling-main)

Copied to clipboard

Challenge: Existing studies have focused on instance-level unlearning, specifically removing predefined instances containing sensitive content.
Approach: They propose a task to erase entity-related knowledge from the target model completely by analyzing the forget set and its size.
Outcome: The proposed task systematically evaluates popular unlearning algorithms and reveals that the knowledge coverage of the forget set and its size play pivotal roles.
To Know or Not To Know? Analyzing Self-Consistency of Large Language Models under Ambiguity (2024.findings-emnlp)

Copied to clipboard

Challenge: Large language models (LLMs) have remarkable performance in a variety of tasks due to factual knowledge accumulated during pre-training.
Approach: They propose an evaluation protocol that disentangles knowing from applying knowledge and test state-of-the-art LLMs on 49 ambiguous entities.
Outcome: The proposed evaluation protocol disentangles knowing from applying knowledge and tests state-of-the-art LLMs on 49 ambiguous entities.
How Do Multilingual Language Models Remember Facts? (2025.findings-acl)

Copied to clipboard

Challenge: Prior research has focused on English monolingual models, but how these mechanisms generalize to non-English languages remains unexplored.
Approach: They analyze three multilingual LLMs to find out how they can generalize recall mechanisms . they find that subject enrichment is language-independent, object extraction is language dependent .
Outcome: The proposed model performs better in multilingual contexts than in English models . the model is more efficient in multi-lingual context, but it is more complex in multilinguistic models compared to English models.
Knowledge Boundary of Large Language Models: A Survey (2025.acl-long)

Copied to clipboard

Challenge: Large language models (LLMs) store vast amount of knowledge in their parameters, but they still have limitations in the memorization and utilization of certain knowledge.
Approach: They propose a comprehensive definition of the LLM knowledge boundary and introduce a formalized taxonomy categorizing knowledge into four distinct types.
Outcome: The proposed definition of the LLM knowledge boundary and taxonomy categorizes knowledge into four distinct types . aims to offer a comprehensive overview, facilitate access to key issues, and inspire further advancements in LLM research.
How do Language Models Reshape Entity Alignment? A Survey of LM-Driven EA Methods: Advances, Benchmarks, and Future (2025.emnlp-main)

Copied to clipboard

Challenge: Entity alignment (EA) is critical for knowledge graph (KG) integration.
Approach: They propose a taxonomy that categorizes methods in three stages: data preparation, feature embedding, and alignment.
Outcome: The proposed taxonomy categorizes methods in three key stages: data preparation, feature embedding, and alignment.
How Do Large Language Models Capture the Ever-changing World Knowledge? A Review of Recent Advances (2023.emnlp-main)

Copied to clipboard

Challenge: Large language models (LLMs) are impressive in solving tasks, but they can quickly be outdated after deployment.
Approach: They provide a review of recent advances in aligning deployed large language models with the ever-changing world knowledge.
Outcome: The proposed models can be used to perform various tasks directly through in-context learning or for further fine-tuning for domain-specific uses.
A Multi-Perspective Analysis of Memorization in Large Language Models (2024.emnlp-main)

Copied to clipboard

Challenge: Large Language Models (LLMs) can generate the same sequences contained in the pre-train corpus, known as memorization.
Approach: They analyze the relationship between memorization and outputs from Large Language Models (LLMs) they show a sudden drop and increase in the frequency of input tokens when generating memorized/unmemorized sequences .
Outcome: The proposed model can generate the same sequences contained in the pre-train corpus, and it can predict unmemorized tokens.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations