Challenge: Rhetorical questions are asked not to seek information, but to persuade or signal stance . how large language models internally represent rhetorical questions remains unclear .
Approach: They analyze rhetorical questions in LLM representations using linear probes on two social-media datasets with different discourse contexts.
Outcome: The results show that rhetorical signals emerge early and are most stably captured by last-token representations.

Similar Papers

Studying Rhetorically Ambiguous Questions (2025.emnlp-main)

Copied to clipboard

Challenge: Existing datasets do not contain many rhetorical questions that can be rhetorical or informational depending on context.
Approach: They propose a dataset explicitly constructed to support the study of rhetorical ambiguity . they evaluate the performance of state-of-the-art language models on the dataset .
Outcome: The proposed dataset shows that state-of-the-art language models struggle to recognize rhetorical questions.
Sparse Neurons Carry Strong Signals of Question Ambiguity in LLMs (2025.emnlp-main)

Copied to clipboard

Challenge: Ambiguity is pervasive in real-world questions, yet large language models often respond with confident answers rather than seeking clarification.
Approach: They show that question ambiguity is linearly encoded in the internal representations of large language models (LLMs) by training linear probes, they identify sparse sets of Ambiguity-Encoding Neurons (AENs)
Outcome: The proposed model outperforms prompting-based and representation-based baselines on ambiguity detection and generalization.
LLM Beliefs Are in Their Heads (2026.acl-long)

Copied to clipboard

Challenge: Using linear controlled probes, we investigate belief-like representations in decoder-only autoregressive LLMs using residual stream activations and single attention heads.
Approach: They develop four different experiments on decoder-only autoregressive LLMs and examine how they fare against these standards.
Outcome: The proposed representations exhibit strong truth sensitivity and consistent accuracy across models and data sets.
Language Directions in Multilingual LLMs: A Layer-wise Diagnostic Study of Token Alignment and Pretraining Imprint (2026.acl-srw)

Copied to clipboard

Challenge: Using a unified probing framework, we analyze six multilingual LLMs across five languages.
Approach: They analyze multilingual representations across five languages and analyze their behavior . they find that accuracy rises by +73.5 to +80.7 points from L0 to L1 on average .
Outcome: The proposed framework enables a consistent and substantial early jump in accuracy across models . the token–language alignment measures where vocabulary sharing peaks .
NewsInterview: a Dataset and a Playground to Evaluate LLMs’ Grounding Gap via Informational Interviews (2025.acl-long)

Copied to clipboard

Challenge: Existing large datasets (1k-10k transcripts) are generated via crowdsourcing and are inherently unnatural.
Approach: They curate a dataset of 40,000 two-person informational interviews from NPR and CNN . they find that LLMs are significantly less likely than human interviewers to use acknowledgements and pivot to higher-level questions.
Outcome: The proposed model is based on 40,000 interviews with journalists and CNN .
A Generalizable Rhetorical Strategy Annotation Model Using LLM-based Debate Simulation and Labelling (2025.findings-emnlp)

Copied to clipboard

Challenge: Rhetorical strategies are important to persuasive communication, but their analysis relies on human annotation, which is costly, inconsistent and difficult to scale.
Approach: They propose a framework that leverages large language models to generate and label debate data . they fine-tune transformer-based classifiers on this dataset and validate it against human data a .
Outcome: The proposed model achieves high performance and strong generalization across topical domains.
Introducing Rhetorical Parallelism Detection: A New Task with Datasets, Metrics, and Baselines (2023.emnlp-main)

Copied to clipboard

Challenge: Parallelism is a common stylistic tool in rhetorical structures, but it is rarely investigated in the field of natural language processing.
Approach: They propose a task of rhetorical parallelism detection to investigate its structure and meaning . they use a Latin and adapted Chinese dataset to define parallelise and define it using a family of metrics .
Outcome: The proposed method achieves F1 scores on Latin and Chinese datasets.
Probing Political Ideology in Large Language Models: How Latent Political Representations Generalize Across Tasks (2025.findings-emnlp)

Copied to clipboard

Challenge: Large language models encode rich internal representations of political ideology, but it remains unclear how these representations contribute to model decision-making.
Approach: They apply inference-time interventions to steer a decoder-only transformer along learned ideological directions . they find that learned ideological representations generalize well to bias detection, but not as well to voting simulations .
Outcome: The proposed model steers a transformer along learned ideological directions . political bias detection, voting preference simulation and bias neutralization are tested .
LLaMAs Have Feelings Too: Unveiling Sentiment and Emotion Representations in LLaMA Models Through Probing (2025.acl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) have become central to NLP, demonstrating their ability to adapt to various tasks through prompting techniques.
Approach: They probe the hidden layers of Large Language Models to identify where sentiment features are most represented and to assess how this affects sentiment analysis.
Outcome: The proposed approach enables sentiment tasks to be performed with memory requirements reduced by an average of 57%.
LLM Tropes: Revealing Fine-Grained Values and Opinions in Large Language Models (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing approaches to evaluate latent values and opinions in large language models suffer from three notable shortcomings.
Approach: They propose to analyze 156k LLM responses to 62 propositions of the Political Compass Test (PCT) generated by 6 LLMs using 420 prompt variations.
Outcome: The proposed analysis of 156k LLM responses to the Political Compass Test (PCT) generated by 6 LLMs shows that tropes are recurrent and consistent across prompts.

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