Rhetorical Questions in LLM Representations: A Linear Probing Study

• URL: http://arxiv.org/abs/2604.14128v1
• Date: Wed, 15 Apr 2026 17:50:56 GMT
• Title: Rhetorical Questions in LLM Representations: A Linear Probing Study
• Abstract summary: We analyze rhetorical questions in LLM representations using linear probes on two social-media datasets with different discourse contexts.<n>We find that rhetorical signals emerge early and are most stably captured by last-token representations.
• Score: 5.165491129638819
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Rhetorical questions are asked not to seek information but to persuade or signal stance. How large language models internally represent them remains unclear. We analyze rhetorical questions in LLM representations using linear probes on two social-media datasets with different discourse contexts, and find that rhetorical signals emerge early and are most stably captured by last-token representations. Rhetorical questions are linearly separable from information-seeking questions within datasets, and remain detectable under cross-dataset transfer, reaching AUROC around 0.7-0.8. However, we demonstrate that transferability does not simply imply a shared representation. Probes trained on different datasets produce different rankings when applied to the same target corpus, with overlap among the top-ranked instances often below 0.2. Qualitative analysis shows that these divergences correspond to distinct rhetorical phenomena: some probes capture discourse-level rhetorical stance embedded in extended argumentation, while others emphasize localized, syntax-driven interrogative acts. Together, these findings suggest that rhetorical questions in LLM representations are encoded by multiple linear directions emphasizing different cues, rather than a single shared direction.

Related papers

• LLMs Encode Relevance as a Layer-Wise Cross-Lingual Signal [8.33491432828288]
  We study whether query-document relevance is linearly decodable from residual-stream activations in instruction-tuned language models.<n>Our results suggest that q-d relevance is encoded as a depth-dependent signal.<n>In several models, validation-selected probes match or outperform generated judgments and better preserve system rankings.
  arXiv  Detail & Related papers  (2026-07-17T01:54:45Z)
• Not What, But How: A Framework for Auditing LLM Responses across Positioning, Generalization, Anthromorphism, and Maxims [54.31707479192195]
  Large language models (LLMs) are being increasingly used to answer subjective, information-seeking questions.<n>Existing evaluations for subjective cultural queries largely focus on factual correctness, ignoring how the response is framed.<n>We introduce FRANZ, an automated FRAmework for respoNse characteriZation to conduct communicative audit of LLM responses along four dimensions.
  arXiv  Detail & Related papers  (2026-06-01T17:01:31Z)
• Multimodal QUD: Inquisitive Questions from Scientific Figures [63.41049609329304]
  We generate inquisitive questions that reach the depth of questions humans generate when engaging with scientific papers.<n>We extend the linguistic theory of Questions Under Discussion (QUD) from being text-only to multimodal.<n>We show that fine-tuning a VLM on MQUD shifts the model from generating generic low-level visual questions to content-specific grounding.
  arXiv  Detail & Related papers  (2026-04-26T14:25:23Z)
• DiscoTrace: Representing and Comparing Answering Strategies of Humans and LLMs in Information-Seeking Question Answering [28.365849533156023]
  We introduce DiscoTrace, a method to identify the rhetorical strategies that answerers use when responding to information-seeking questions.<n>Applying DiscoTrace to answers from nine different human communities reveals that communities have diverse preferences for answer construction.
  arXiv  Detail & Related papers  (2026-04-16T15:17:36Z)
• Prompt-Response Semantic Divergence Metrics for Faithfulness Hallucination and Misalignment Detection in Large Language Models [0.0]
  This paper introduces Semantic Divergence Metrics (SDM), a novel framework for detecting Faithfulness Hallucinations.<n>A heatmap of topic co-occurances between prompts and responses can be viewed as a quantified two-dimensional visualization of the user-machine dialogue.
  arXiv  Detail & Related papers  (2025-08-13T20:55:26Z)
• ELOQ: Resources for Enhancing LLM Detection of Out-of-Scope Questions [52.33835101586687]
  We study out-of-scope questions, where the retrieved document appears semantically similar to the question but lacks the necessary information to answer it.<n>We propose a guided hallucination-based approach ELOQ to automatically generate a diverse set of out-of-scope questions from post-cutoff documents.
  arXiv  Detail & Related papers  (2024-10-18T16:11:29Z)
• Towards Reliable and Factual Response Generation: Detecting Unanswerable Questions in Information-Seeking Conversations [16.99952884041096]
  Generative AI models face the challenge of hallucinations that can undermine users' trust in such systems. We approach the problem of conversational information seeking as a two-step process, where relevant passages in a corpus are identified first and then summarized into a final system response. Specifically, our proposed method employs a sentence-level classifier to detect if the answer is present, then aggregates these predictions on the passage level, and eventually across the top-ranked passages to arrive at a final answerability estimate.
  arXiv  Detail & Related papers  (2024-01-21T10:15:36Z)
• Distributed Marker Representation for Ambiguous Discourse Markers and Entangled Relations [50.31129784616845]
  We learn a Distributed Marker Representation (DMR) by utilizing the unlimited discourse marker data with a latent discourse sense. Our method also offers a valuable tool to understand complex ambiguity and entanglement among discourse markers and manually defined discourse relations.
  arXiv  Detail & Related papers  (2023-06-19T00:49:51Z)
• An Information-Theoretic Analysis of Self-supervised Discrete Representations of Speech [17.07957283733822]
  We develop an information-theoretic framework whereby we represent each phonetic category as a distribution over discrete units. Our study demonstrates that the entropy of phonetic distributions reflects the variability of the underlying speech sounds. While our study confirms the lack of direct, one-to-one correspondence, we find an intriguing, indirect relationship between phonetic categories and discrete units.
  arXiv  Detail & Related papers  (2023-06-04T16:52:11Z)
• Using Natural Language Explanations to Rescale Human Judgments [81.66697572357477]
  We propose a method to rescale ordinal annotations and explanations using large language models (LLMs)<n>We feed annotators' Likert ratings and corresponding explanations into an LLM and prompt it to produce a numeric score anchored in a scoring rubric.<n>Our method rescales the raw judgments without impacting agreement and brings the scores closer to human judgments grounded in the same scoring rubric.
  arXiv  Detail & Related papers  (2023-05-24T06:19:14Z)
• Syntactic Perturbations Reveal Representational Correlates of Hierarchical Phrase Structure in Pretrained Language Models [22.43510769150502]
  It is not entirely clear what aspects of sentence-level syntax are captured by vector-based language representations. We show that Transformers build sensitivity to larger parts of the sentence along their layers, and that hierarchical phrase structure plays a role in this process.
  arXiv  Detail & Related papers  (2021-04-15T16:30:31Z)
• Did they answer? Subjective acts and intents in conversational discourse [48.63528550837949]
  We present the first discourse dataset with multiple and subjective interpretations of English conversation. We show disagreements are nuanced and require a deeper understanding of the different contextual factors.
  arXiv  Detail & Related papers  (2021-04-09T16:34:19Z)
• Pareto Probing: Trading Off Accuracy for Complexity [87.09294772742737]
  We argue for a probe metric that reflects the fundamental trade-off between probe complexity and performance. Our experiments with dependency parsing reveal a wide gap in syntactic knowledge between contextual and non-contextual representations.
  arXiv  Detail & Related papers  (2020-10-05T17:27:31Z)
• Multi-Stage Conversational Passage Retrieval: An Approach to Fusing Term Importance Estimation and Neural Query Rewriting [56.268862325167575]
  We tackle conversational passage retrieval (ConvPR) with query reformulation integrated into a multi-stage ad-hoc IR system. We propose two conversational query reformulation (CQR) methods: (1) term importance estimation and (2) neural query rewriting. For the former, we expand conversational queries using important terms extracted from the conversational context with frequency-based signals. For the latter, we reformulate conversational queries into natural, standalone, human-understandable queries with a pretrained sequence-tosequence model.
  arXiv  Detail & Related papers  (2020-05-05T14:30:20Z)

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.