Challenge: High-dimensional dense embeddings extracted by large language models pose memory requirements and high computation time.
Approach: They propose a method that maps high-dimensional dense embeddings to lower-dimensional sparse representations while preserving crucial anomaly characteristics.
Outcome: The proposed method achieves better detection performance than 11 SOTA anomaly detection algorithms while maintaining computational efficiency and low memory cost.

Similar Papers

LLMs Meet Isolation Kernel: Lightweight, Learning-free Binary Embeddings for Fast Retrieval (2026.findings-acl)

Copied to clipboard

Challenge: Large language models (LLMs) embeddings are typically high-dimensional, leading to substantial storage and retrieval overhead.
Approach: They propose a learning-free method that transforms an LLM embedding into a binary embeddable using Isolation Kernel (IKE).
Outcome: The proposed method performs 16.7 faster retrieval and 16 lower memory usage than the original LLM embeddings while maintaining comparable accuracy.
Enhancing Two Steps Textual Anomaly Detection through Anisotropy Mitigation (2026.acl-long)

Copied to clipboard

Challenge: Recent approaches to anomaly detection focus on embeddings from pre-trained models . however, the geometric properties of pre-training embedders can hinder detection algorithms .
Approach: They propose to apply anomaly detection algorithms to embeddings from pre-trained models to improve accuracy.
Outcome: The proposed approach improves similarity-trained models by adapting embeddings to assumptions made by classical detection algorithms.
Large Language Models for Anomaly and Out-of-Distribution Detection: A Survey (2025.findings-naacl)

Copied to clipboard

Challenge: Large Language Models (LLMs) have demonstrated their effectiveness in natural language processing but also in broader applications due to their advanced comprehension and generative capabilities.
Approach: They propose a taxonomy to categorize existing approaches into two classes based on the role played by LLMs.
Outcome: The proposed taxonomy categorizes existing approaches into two classes based on the role played by LLMs.
AD-NLP: A Benchmark for Anomaly Detection in Natural Language Processing (2023.emnlp-main)

Copied to clipboard

Challenge: Methods for Anomaly Detection in text have shown strong empirical results on ad-hoc anomaly setups that are usually made by downsampling some classes of a labeled dataset.
Approach: They propose a unified benchmark for detecting various types of anomalies . they evaluate two strong shallow baselines and two current state-of-the-art neural approaches .
Outcome: The proposed benchmarks provide insights into the knowledge the neural models are learning when performing the task.
Improving Text Embeddings with Large Language Models (2024.acl-long)

Copied to clipboard

Challenge: Existing methods for obtaining text embeddings require complex training pipelines . authors leverage proprietary LLMs to generate diverse synthetic data for text embeds based on 93 languages .
Approach: They propose a method for obtaining high-quality text embeddings using only synthetic data and less than 1k training steps.
Outcome: The proposed method achieves strong performance on competitive text embedding benchmarks without using any labeled data.
Large Language Models Are Better Adversaries: Exploring Generative Clean-Label Backdoor Attacks Against Text Classifiers (2023.findings-emnlp)

Copied to clipboard

Challenge: Backdoor attacks manipulate model predictions by inserting malicious "poison" instances that contain a specific pattern or "trigger."
Approach: They propose an attack that inserts style-based triggers into training and test data by using a poison selection technique to improve the effectiveness of both LLMBkd and existing backdoor attacks.
Outcome: The proposed attack achieves high success rates across a wide range of styles with little effort and no model training.
LDIR: Low-Dimensional Dense and Interpretable Text Embeddings with Relative Representations (2025.findings-acl)

Copied to clipboard

Challenge: Existing text embeddings with high dimensions are difficult to trace and interpret.
Approach: They propose low-dimensional and interpretable text embeddings with relative representations that encode semantic meanings in a vector space where similar texts are close together in the representation space.
Outcome: The proposed embeddings outperform existing models on multiple tasks with fewer dimensions and are lowdimensional and dense while maintaining interpretability.
Breaking the Generator Barrier: Disentangled Representation for Generalizable AI-Text Detection (2026.acl-long)

Copied to clipboard

Challenge: a rapid proliferation of large language models (LLMs) generate text that increasingly resembles human writing . this makes it difficult to capture subtle cues that distinguish AI-generated content from human-written content .
Approach: They propose a framework that disentangles AI-detection semantics from generator-aware artifacts by latent encoding and perturbation-based regularization.
Outcome: The proposed framework disentangles AI-detection semantics from generator-aware artifacts on 20 representative LLMs across 7 categories.
Unsupervised Anomaly Detection in Multi-Topic Short-Text Corpora (2023.eacl-main)

Copied to clipboard

Challenge: Unsupervised anomaly detection is a challenging task when the majority class is heterogeneous.
Approach: They propose to use word embeddings to represent each sample by a dense vector and use a Mixture Model approach to detect which samples deviate the most from the underlying distributions of the corpus.
Outcome: The proposed method is more efficient than state-of-the-art methods on real datasets.
Can LLMs Find a Needle in a Haystack? A Look at Anomaly Detection Language Modeling (2025.findings-emnlp)

Copied to clipboard

Challenge: Anomaly detection (AD) is a problem in machine learning, but it is not always competitive on certain datasets.
Approach: They propose a new approach to Anomaly detection based on large pre-trained language models in three modalities.
Outcome: The proposed model beats baselines on anomaly detection when presented as imbalanced classification problem regardless of the concentration of anomalous samples.

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