Large Language Models for Subjective Language Understanding: A Survey

Subjective language understanding refers to a broad set of natural language processing tasks where the goal is to interpret or generate content that conveys personal feelings, opinions, or figurative meanings rather than objective facts. With the advent of large language models (LLMs) such as ChatGPT, LLaMA, and others, there has been a paradigm shift in how we approach these inherently nuanced tasks. In this survey, we provide a comprehensive review of recent advances in applying LLMs to subjective language tasks, including sentiment analysis, emotion recognition, sarcasm detection, humor understanding, stance detection, metaphor interpretation, intent detection, and aesthetics assessment. We begin by clarifying the definition of subjective language from linguistic and cognitive perspectives, and we outline the unique challenges posed by subjective language (e.g. ambiguity, figurativeness, context dependence). We then survey the evolution of LLM architectures and techniques that particularly benefit subjectivity tasks, highlighting why LLMs are well-suited to model subtle human-like judgments. For each of the eight tasks, we summarize task definitions, key datasets, state-of-the-art LLM-based methods, and remaining challenges. We provide comparative insights, discussing commonalities and differences among tasks and how multi-task LLM approaches might yield unified models of subjectivity. Finally, we identify open issues such as data limitations, model bias, and ethical considerations, and suggest future research directions. We hope this survey will serve as a valuable resource for researchers and practitioners interested in the intersection of affective computing, figurative language processing, and large-scale language models.

Enhancing Rumor Detection Methods with Propagation Structure Infused Language Model

Pretrained Language Models (PLMs) have excelled in various Natural Language Processing tasks, benefiting from large-scale pretraining and self-attention mechanism's ability to capture long-range dependencies. However, their performance on social media application tasks like rumor detection remains suboptimal. We attribute this to mismatches between pretraining corpora and social texts, inadequate handling of unique social symbols, and pretraining tasks ill-suited for modeling user engagements implicit in propagation structures. To address these issues, we propose a continue pretraining strategy called Post Engagement Prediction (PEP) to infuse information from propagation structures into PLMs. PEP makes models to predict root, branch, and parent relations between posts, capturing interactions of stance and sentiment crucial for rumor detection. We also curate and release large-scale Twitter corpus: TwitterCorpus (269GB text), and two unlabeled claim conversation datasets with propagation structures (UTwitter and UWeibo). Utilizing these resources and PEP strategy, we train a Twitter-tailored PLM called SoLM. Extensive experiments demonstrate PEP significantly boosts rumor detection performance across universal and social media PLMs, even in few-shot scenarios. On benchmark datasets, PEP enhances baseline models by 1.0-3.7\% accuracy, even enabling it to outperform current state-of-the-art methods on multiple datasets. SoLM alone, without high-level modules, also achieves competitive results, highlighting the strategy's effectiveness in learning discriminative post interaction features.

Propagation Tree Is Not Deep: Adaptive Graph Contrastive Learning Approach for Rumor Detection

Rumor detection on social media has become increasingly important. Most existing graph-based models presume rumor propagation trees (RPTs) have deep structures and learn sequential stance features along branches. However, through statistical analysis on real-world datasets, we find RPTs exhibit wide structures, with most nodes being shallow 1-level replies. To focus learning on intensive substructures, we propose Rumor Adaptive Graph Contrastive Learning (RAGCL) method with adaptive view augmentation guided by node centralities. We summarize three principles for RPT augmentation: 1) exempt root nodes, 2) retain deep reply nodes, 3) preserve lower-level nodes in deep sections. We employ node dropping, attribute masking and edge dropping with probabilities from centrality-based importance scores to generate views. A graph contrastive objective then learns robust rumor representations. Extensive experiments on four benchmark datasets demonstrate RAGCL outperforms state-of-the-art methods. Our work reveals the wide-structure nature of RPTs and contributes an effective graph contrastive learning approach tailored for rumor detection through principled adaptive augmentation. The proposed principles and augmentation techniques can potentially benefit other applications involving tree-structured graphs.

Learning the Topic, Not the Language: How LLMs Classify Online Immigration Discourse Across Languages

Large language models (LLMs) are transforming social-science research by enabling scalable, precise analysis. Their adaptability raises the question of whether knowledge acquired through fine-tuning in a few languages can transfer to unseen languages that only appeared during pre-training. To examine this, we fine-tune lightweight LLaMA 3.2-3B models on monolingual, bilingual, or multilingual data sets to classify immigration-related tweets from X/Twitter across 13 languages, a domain characterised by polarised, culturally specific discourse. We evaluate whether minimal language-specific fine-tuning enables cross-lingual topic detection and whether adding targeted languages corrects pre-training biases. Results show that LLMs fine-tuned in one or two languages can reliably classify immigration-related content in unseen languages. However, identifying whether a tweet expresses a pro- or anti-immigration stance benefits from multilingual fine-tuning. Pre-training bias favours dominant languages, but even minimal exposure to under-represented languages during fine-tuning (as little as $9.62\times10^{-11}$ of the original pre-training token volume) yields significant gains. These findings challenge the assumption that cross-lingual mastery requires extensive multilingual training: limited language coverage suffices for topic-level generalisation, and structural biases can be corrected with lightweight interventions. By releasing 4-bit-quantised, LoRA fine-tuned models, we provide an open-source, reproducible alternative to proprietary LLMs that delivers 35 times faster inference at just 0.00000989% of the dollar cost of the OpenAI GPT-4o model, enabling scalable, inclusive research.

Is External Information Useful for Stance Detection with LLMs?

In the stance detection task, a text is classified as either favorable, opposing, or neutral towards a target. Prior work suggests that the use of external information, e.g., excerpts from Wikipedia, improves stance detection performance. However, whether or not such information can benefit large language models (LLMs) remains an unanswered question, despite their wide adoption in many reasoning tasks. In this study, we conduct a systematic evaluation on how Wikipedia and web search external information can affect stance detection across eight LLMs and in three datasets with 12 targets. Surprisingly, we find that such information degrades performance in most cases, with macro F1 scores dropping by up to 27.9\%. We explain this through experiments showing LLMs' tendency to align their predictions with the stance and sentiment of the provided information rather than the ground truth stance of the given text. We also find that performance degradation persists with chain-of-thought prompting, while fine-tuning mitigates but does not fully eliminate it. Our findings, in contrast to previous literature on BERT-based systems which suggests that external information enhances performance, highlight the risks of information biases in LLM-based stance classifiers. Code is available at https://github.com/ngqm/acl2025-stance-detection.

Abstract, Align, Predict: Zero-Shot Stance Detection via Cognitive Inductive Reasoning

Zero-shot stance detection (ZSSD) aims to identify the stance of text toward previously unseen targets, a setting where conventional supervised models often fail due to reliance on labeled data and shallow lexical cues. Inspired by human cognitive reasoning, we propose the Cognitive Inductive Reasoning Framework (CIRF), which abstracts transferable reasoning schemas from unlabeled text and encodes them as concept-level logic. To integrate these schemas with input arguments, we introduce a Schema-Enhanced Graph Kernel Model (SEGKM) that dynamically aligns local and global reasoning structures. Experiments on SemEval-2016, VAST, and COVID-19-Stance benchmarks show that CIRF establishes new state-of-the-art results, outperforming strong ZSSD baselines by 1.0, 4.5, and 3.3 percentage points in macro-F1, respectively, and achieving comparable accuracy with 70\% fewer labeled examples. We will release the full code upon publication.

PolitiSky24: U.S. Political Bluesky Dataset with User Stance Labels

Stance detection identifies the viewpoint expressed in text toward a specific target, such as a political figure. While previous datasets have focused primarily on tweet-level stances from established platforms, user-level stance resources, especially on emerging platforms like Bluesky remain scarce. User-level stance detection provides a more holistic view by considering a user's complete posting history rather than isolated posts. We present the first stance detection dataset for the 2024 U.S. presidential election, collected from Bluesky and centered on Kamala Harris and Donald Trump. The dataset comprises 16,044 user-target stance pairs enriched with engagement metadata, interaction graphs, and user posting histories. PolitiSky24 was created using a carefully evaluated pipeline combining advanced information retrieval and large language models, which generates stance labels with supporting rationales and text spans for transparency. The labeling approach achieves 81\% accuracy with scalable LLMs. This resource addresses gaps in political stance analysis through its timeliness, open-data nature, and user-level perspective. The dataset is available at https://doi.org/10.5281/zenodo.15616911

Human-Aligned Faithfulness in Toxicity Explanations of LLMs

The discourse around toxicity and LLMs in NLP largely revolves around detection tasks. This work shifts the focus to evaluating LLMs' reasoning about toxicity -- from their explanations that justify a stance -- to enhance their trustworthiness in downstream tasks. Despite extensive research on explainability, it is not straightforward to adopt existing methods to evaluate free-form toxicity explanation due to their over-reliance on input text perturbations, among other challenges. To account for these, we propose a novel, theoretically-grounded multi-dimensional criterion, Human-Aligned Faithfulness (HAF), that measures the extent to which LLMs' free-form toxicity explanations align with those of a rational human under ideal conditions. We develop six metrics, based on uncertainty quantification, to comprehensively evaluate \haf of LLMs' toxicity explanations with no human involvement, and highlight how "non-ideal" the explanations are. We conduct several experiments on three Llama models (of size up to 70B) and an 8B Ministral model on five diverse toxicity datasets. Our results show that while LLMs generate plausible explanations to simple prompts, their reasoning about toxicity breaks down when prompted about the nuanced relations between the complete set of reasons, the individual reasons, and their toxicity stances, resulting in inconsistent and nonsensical responses. We open-source our code and LLM-generated explanations at https://github.com/uofthcdslab/HAF.

CL-ISR: A Contrastive Learning and Implicit Stance Reasoning Framework for Misleading Text Detection on Social Media

Misleading text detection on social media platforms is a critical research area, as these texts can lead to public misunderstanding, social panic and even economic losses. This paper proposes a novel framework - CL-ISR (Contrastive Learning and Implicit Stance Reasoning), which combines contrastive learning and implicit stance reasoning, to improve the detection accuracy of misleading texts on social media. First, we use the contrastive learning algorithm to improve the model's learning ability of semantic differences between truthful and misleading texts. Contrastive learning could help the model to better capture the distinguishing features between different categories by constructing positive and negative sample pairs. This approach enables the model to capture distinguishing features more effectively, particularly in linguistically complicated situations. Second, we introduce the implicit stance reasoning module, to explore the potential stance tendencies in the text and their relationships with related topics. This method is effective for identifying content that misleads through stance shifting or emotional manipulation, because it can capture the implicit information behind the text. Finally, we integrate these two algorithms together to form a new framework, CL-ISR, which leverages the discriminative power of contrastive learning and the interpretive depth of stance reasoning to significantly improve detection effect.

Emotion-aware Dual Cross-Attentive Neural Network with Label Fusion for Stance Detection in Misinformative Social Media Content

The rapid evolution of social media has generated an overwhelming volume of user-generated content, conveying implicit opinions and contributing to the spread of misinformation. The method aims to enhance the detection of stance where misinformation can polarize user opinions. Stance detection has emerged as a crucial approach to effectively analyze underlying biases in shared information and combating misinformation. This paper proposes a novel method for \textbf{S}tance \textbf{P}rediction through a \textbf{L}abel-fused dual cross-\textbf{A}ttentive \textbf{E}motion-aware neural \textbf{Net}work (SPLAENet) in misinformative social media user-generated content. The proposed method employs a dual cross-attention mechanism and a hierarchical attention network to capture inter and intra-relationships by focusing on the relevant parts of source text in the context of reply text and vice versa. We incorporate emotions to effectively distinguish between different stance categories by leveraging the emotional alignment or divergence between the texts. We also employ label fusion that uses distance-metric learning to align extracted features with stance labels, improving the method's ability to accurately distinguish between stances. Extensive experiments demonstrate the significant improvements achieved by SPLAENet over existing state-of-the-art methods. SPLAENet demonstrates an average gain of 8.92\% in accuracy and 17.36\% in F1-score on the RumourEval dataset. On the SemEval dataset, it achieves average gains of 7.02\% in accuracy and 10.92\% in F1-score. On the P-stance dataset, it demonstrates average gains of 10.03\% in accuracy and 11.18\% in F1-score. These results validate the effectiveness of the proposed method for stance detection in the context of misinformative social media content.