Pith. sign in

REVIEW 7 cited by

Envisioning Outlier Exposure by Large Language Models for Out-of-Distribution Detection

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2406.00806 v1 pith:MYBOCUVP submitted 2024-06-02 cs.LG

Chentao Cao , Zhun Zhong , Zhanke Zhou , Yang Liu , Tongliang Liu , Bo Han This is my paper
classification cs.LG
keywords detectionmodelsoutlierlargepotentialsamplescapabilityclip
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Detecting out-of-distribution (OOD) samples is essential when deploying machine learning models in open-world scenarios. Zero-shot OOD detection, requiring no training on in-distribution (ID) data, has been possible with the advent of vision-language models like CLIP. Existing methods build a text-based classifier with only closed-set labels. However, this largely restricts the inherent capability of CLIP to recognize samples from large and open label space. In this paper, we propose to tackle this constraint by leveraging the expert knowledge and reasoning capability of large language models (LLM) to Envision potential Outlier Exposure, termed EOE, without access to any actual OOD data. Owing to better adaptation to open-world scenarios, EOE can be generalized to different tasks, including far, near, and fine-grained OOD detection. Technically, we design (1) LLM prompts based on visual similarity to generate potential outlier class labels specialized for OOD detection, as well as (2) a new score function based on potential outlier penalty to distinguish hard OOD samples effectively. Empirically, EOE achieves state-of-the-art performance across different OOD tasks and can be effectively scaled to the ImageNet-1K dataset. The code is publicly available at: https://github.com/tmlr-group/EOE.

Discussion (0). Sign in to comment.

Forward citations

Cited by 7 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. NegAS: Negative Label Guided Attention and Scoring for Out-of-Distribution Object Detection with Vision-Language Models

    cs.CV 2026-06 unverdicted novelty 7.0 of 10

    NegAS uses negative labels for attention guidance and sigmoid scoring to improve OOD detection in VLM-based object detectors while preserving ID performance.

  2. Representation Trajectories Matters: Complementary Evidence for OOD Detection and Image Classification

    cs.CV 2026-07 accept novelty 6.0 of 10

    Recording how an image's representation evolves block-by-block, relative to learned class routes, improves OOD detection in 131/152 comparisons and clean classification in 71/72 model–dataset cases.

  3. Benchmarking and Improving Monitors for Out-Of-Distribution Alignment Failure in LLMs

    cs.AI 2026-05 unverdicted novelty 6.0 of 10

    MOOD benchmark shows guard models fail to generalize to OOD alignment failures in LLMs, but combining them with Mahalanobis and perplexity OOD detectors improves recall from 39% to 45% with better scaling than larger ...

  4. Benchmarking and Improving Monitors for Out-Of-Distribution Alignment Failure in LLMs

    cs.AI 2026-05 conditional novelty 6.0 of 10

    Introduces MOOD benchmark for OOD LLM alignment failures and shows guard models plus Mahalanobis and perplexity OOD detectors improve recall from 39% to 45% with positive scaling.

  5. A Taxonomy of Cognitive Capability Gaps in Generative and Agentic AI

    cs.AI 2026-08 conditional novelty 5.0 of 10

    The paper organizes persistent AI limitations into a five-part taxonomy of cognitive capability gaps and proposes a conceptual ACIA architecture and cognition-centric metrics, none of which are validated.

  6. Node-to-Neighborhood Semantic Consistency: Text-Topology Alignment for TAGs Anomaly Detection

    cs.CL 2026-06 unverdicted novelty 5.0 of 10

    N2NSC framework detects anomalies in text-attributed graphs by enforcing node-to-neighborhood semantic consistency via two complementary fusion paths that align textual semantics with topology.

  7. Knowledge Regularized Negative Feature Tuning of Vision-Language Models for Out-of-Distribution Detection

    cs.CV 2025-07 conditional novelty 5.0 of 10

    KR-NFT tunes CLIP text features with image-conditioned scaling and shifting plus a knowledge regularization loss, improving OOD detection on base and unseen classes without forgetting pre-trained knowledge.

Pith tools