You Frame It: How Conceptual Representations Shape LLM Detection and Reasoning about Antisemitism

• URL: http://arxiv.org/abs/2607.04945v1
• Date: Mon, 06 Jul 2026 11:20:18 GMT
• Title: You Frame It: How Conceptual Representations Shape LLM Detection and Reasoning about Antisemitism
• Abstract summary: We investigate how different forms of conceptual grounding affect antisemitism detection and explanation behavior.<n>We find that fine-grained taxonomic representations substantially improve recall, while simultaneously reducing precision.<n>Post-Holocaust antisemitism poses the most persistent challenge across models and configurations.
• Score: 0.17188280334580197
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: LLMs enable the integration of external conceptual resources at inference time, creating new opportunities for detecting ideologically and historically complex phenomena such as antisemitism. We investigate how different forms of conceptual grounding affect antisemitism detection and explanation behavior across four state-of-the-art LLMs. Using two expert-annotated datasets, we compare definitional, fine-grained taxonomic, example-augmented, and large-context representations of antisemitism. We find that fine-grained taxonomic representations substantially improve recall, while simultaneously reducing precision. Surprisingly, supplying substantially larger conceptual resources yields no additional quantitative benefit. Post-Holocaust antisemitism poses the most persistent challenge across models and configurations. Analysis of explanations further reveals systematic limitations including overproduction of conceptual references, reliance on lexical cues, overconfidence, and difficulties with subtle or justificatory forms of antisemitism. Our findings highlight both the potential and the remaining limitations of conceptually grounded LLMs for antisemitism detection and reasoning.

Related papers

• From "What-If" to "What-Is": Counterfactual Thinking-Inspired Semantic Alignment for Visual Brain Decoding [21.204310001308077]
  Visual brain decoding reconstructs visual content perceived by a person from neural measurements such as fMRI.<n>We propose ConceptAlign, a counterfactual semantic alignment framework for visual brain decoding.<n>We introduce a systematic three-level semantic evaluation framework covering foundational discriminability, counterfactual semantic discrimination, and representational geometry.
  arXiv  Detail & Related papers  (2026-08-15T10:40:53Z)
• Evaluating Large Language Models for Antisemitic Incident Classification [64.21103964951531]
  We introduce the task of hateful event detection and investigate the ability of AI systems to discover and classify reports of antisemitic events with fine-grained labels.<n>We evaluate OpenAI's GPT-4o and Meta's Llama-3.2-3B-Instruct on datasets containing antisemitic event descriptions from news articles, civil society reports, and official records.
  arXiv  Detail & Related papers  (2026-07-06T10:14:53Z)
• Perception Without Engagement: Dissecting the Causal Discovery Deficit in LMMs [68.58207076756237]
  We introduce ProCauEval, a perturbation-based evaluation protocol that shifts from outcome assessment to mechanism diagnosis.<n>We find that models faithfully perceive video content yet systematically underexploit it during causal reasoning.<n>We propose Anti-Distillation Policy Optimization (ADPO), a reinforcement learning framework built on negative teacher alignment.
  arXiv  Detail & Related papers  (2026-05-10T08:48:58Z)
• Evaluating Large Language Models for Detecting Antisemitism [4.368443030353556]
  We evaluate eight open-source machine-learning models' capability to detect antisemitic content.<n>We design a new CoT-like prompt, Guided-CoT, and find that injecting domain-specific thoughts increases performance and utility.
  arXiv  Detail & Related papers  (2025-09-22T18:23:21Z)
• Beyond Prompt-Induced Lies: Investigating LLM Deception on Benign Prompts [79.1081247754018]
  Large Language Models (LLMs) are widely deployed in reasoning, planning, and decision-making tasks.<n>We propose a framework based on Contact Searching Questions(CSQ) to quantify the likelihood of deception.
  arXiv  Detail & Related papers  (2025-08-08T14:46:35Z)
• Machine Bullshit: Characterizing the Emergent Disregard for Truth in Large Language Models [57.834711966432685]
  Bullshit, as conceptualized by philosopher Harry Frankfurt, refers to statements made without regard to their truth value.<n>We introduce the Bullshit Index, a novel metric quantifying large language model's indifference to truth.<n>We observe prevalent machine bullshit in political contexts, with weasel words as the dominant strategy.
  arXiv  Detail & Related papers  (2025-07-10T07:11:57Z)
• RealEra: Semantic-level Concept Erasure via Neighbor-Concept Mining [25.769144703607214]
  Concept erasure has been proposed to remove the model's knowledge about protected and inappropriate concepts. We propose RealEra to address this "concept residue" issue. We show that RealEra outperforms previous concept erasing methods in terms of superior erasing efficacy, specificity, and generality.
  arXiv  Detail & Related papers  (2024-10-11T17:55:30Z)
• A Theory for Token-Level Harmonization in Retrieval-Augmented Generation [76.75124161306795]
  Retrieval-augmented generation (RAG) utilizes retrieved texts to enhance large language models (LLMs)<n>This paper provides a theory to explain and trade off the benefit and detriment in RAG.<n>Based on our theory, we propose a practical novel method, Tok-RAG, which achieves collaborative generation between the pure LLM and RAG.
  arXiv  Detail & Related papers  (2024-06-03T02:56:14Z)
• Concept Arithmetics for Circumventing Concept Inhibition in Diffusion Models [58.065255696601604]
  We use compositional property of diffusion models, which allows to leverage multiple prompts in a single image generation. We argue that it is essential to consider all possible approaches to image generation with diffusion models that can be employed by an adversary.
  arXiv  Detail & Related papers  (2024-04-21T16:35:16Z)
• Towards Uncovering How Large Language Model Works: An Explainability Perspective [38.07611356855978]
  Large language models (LLMs) have led to breakthroughs in language tasks, yet the internal mechanisms that enable their remarkable generalization and reasoning abilities remain opaque. This paper aims to uncover the mechanisms underlying LLM functionality through the lens of explainability.
  arXiv  Detail & Related papers  (2024-02-16T13:46:06Z)
• Avalon's Game of Thoughts: Battle Against Deception through Recursive Contemplation [80.126717170151]
  This study utilizes the intricate Avalon game as a testbed to explore LLMs' potential in deceptive environments. We introduce a novel framework, Recursive Contemplation (ReCon), to enhance LLMs' ability to identify and counteract deceptive information.
  arXiv  Detail & Related papers  (2023-10-02T16:27:36Z)
• "Subverting the Jewtocracy": Online Antisemitism Detection Using Multimodal Deep Learning [23.048101866010445]
  We present the first work in the direction of automated multimodal detection of online antisemitism. We label two datasets with 3,102 and 3,509 social media posts from Twitter and Gab respectively. We present a multimodal deep learning system that detects the presence of antisemitic content and its specific antisemitism category using text and images from posts.
  arXiv  Detail & Related papers  (2021-04-13T05:22:55Z)

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.