Is External Information Useful for Stance Detection with LLMs?

• URL: http://arxiv.org/abs/2507.01543v1
• Date: Wed, 02 Jul 2025 09:53:41 GMT
• Title: Is External Information Useful for Stance Detection with LLMs?
• Abstract summary: Prior work suggests that the use of external information, e.g., excerpts from Wikipedia, improves stance detection performance.<n>We conduct a systematic evaluation on how Wikipedia and web search external information can affect stance detection.<n>We find that such information degrades performance in most cases, with macro F1 scores dropping by up to 27.9%.
• Score: 1.0610707915233728
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Contextualized Prompting For Stance Detection On Social Media [41.666445939998454]
  Stance detection on social media is challenging due to short, noisy, and context-dependent language.<n>We investigate the impact of incorporating contextual information into large language models.<n>We find that integrating contextual information improves performance, but only under specific conditions.
  arXiv  Detail & Related papers  (2026-06-04T11:14:44Z)
• Data, Not Model: Explaining Bias toward LLM Texts in Neural Retrievers [76.92519309816008]
  Recent studies show that neural retrievers often display source bias, favoring passages generated by LLMs over human-written ones.<n>This bias has been considered an inherent flaw of retrievers, raising concerns about the fairness and reliability of modern information access systems.<n>Our work challenges this view by showing that source bias stems from supervision in retrieval datasets rather than the models themselves.
  arXiv  Detail & Related papers  (2026-04-07T17:57:07Z)
• Large Language Model Hacking: Quantifying the Hidden Risks of Using LLMs for Text Annotation [66.84286617519258]
  Large language models are transforming social science research by enabling the automation of labor-intensive tasks like data annotation and text analysis.<n>Such variation can introduce systematic biases and random errors, which propagate to downstream analyses and cause Type I (false positive), Type II (false negative), Type S (wrong sign), or Type M (exaggerated effect) errors.<n>We find that intentional LLM hacking is strikingly simple. By replicating 37 data annotation tasks from 21 published social science studies, we show that, with just a handful of prompt paraphrases, virtually anything can be presented as statistically significant.
  arXiv  Detail & Related papers  (2025-09-10T17:58:53Z)
• Positional Biases Shift as Inputs Approach Context Window Limits [57.00239097102958]
  The LiM effect is strongest when inputs occupy up to 50% of a model's context window.<n>We observe a distance-based bias, where model performance is better when relevant information is closer to the end of the input.
  arXiv  Detail & Related papers  (2025-08-10T20:40:24Z)
• Small Encoders Can Rival Large Decoders in Detecting Groundedness [45.13986921082049]
  Augmenting large language models (LLMs) with external context significantly improves their performance in natural language processing (NLP) tasks.<n>This study focuses on detecting whether a given query is grounded in a document provided in context before the costly answer generation by LLMs.<n>We show that lightweight, task specific encoder models such as RoBERTa and NomicBERT, fine-tuned on curated datasets, can achieve accuracy comparable to state-of-the-art LLMs.
  arXiv  Detail & Related papers  (2025-06-26T14:09:41Z)
• Verifying the Verifiers: Unveiling Pitfalls and Potentials in Fact Verifiers [59.168391398830515]
  We evaluate 12 pre-trained LLMs and one specialized fact-verifier, using a collection of examples from 14 fact-checking benchmarks.<n>We highlight the importance of addressing annotation errors and ambiguity in datasets.<n> frontier LLMs with few-shot in-context examples, often overlooked in previous works, achieve top-tier performance.
  arXiv  Detail & Related papers  (2025-06-16T10:32:10Z)
• How does Misinformation Affect Large Language Model Behaviors and Preferences? [37.06385727015972]
  Large Language Models (LLMs) have shown remarkable capabilities in knowledge-intensive tasks.<n>We present MisBench, the current largest and most comprehensive benchmark for evaluating LLMs' behavior and knowledge preference toward misinformation.<n> Empirical results reveal that while LLMs demonstrate comparable abilities in discerning misinformation, they still remain susceptible to knowledge conflicts and stylistic variations.
  arXiv  Detail & Related papers  (2025-05-27T17:57:44Z)
• Unraveling Misinformation Propagation in LLM Reasoning [19.89817963822589]
  We show how misinformation propagates within Large Language Models' reasoning process.<n>Applying factual corrections early in the reasoning process most effectively reduces misinformation propagation.<n>Our work offers a practical approach to mitigating misinformation propagation.
  arXiv  Detail & Related papers  (2025-05-24T06:45:45Z)
• Defending against Indirect Prompt Injection by Instruction Detection [81.98614607987793]
  We propose a novel approach that takes external data as input and leverages the behavioral state of LLMs during both forward and backward propagation to detect potential IPI attacks.<n>Our approach achieves a detection accuracy of 99.60% in the in-domain setting and 96.90% in the out-of-domain setting, while reducing the attack success rate to just 0.12% on the BIPIA benchmark.
  arXiv  Detail & Related papers  (2025-05-08T13:04:45Z)
• Exploring Automatic Cryptographic API Misuse Detection in the Era of LLMs [60.32717556756674]
  This paper introduces a systematic evaluation framework to assess Large Language Models in detecting cryptographic misuses. Our in-depth analysis of 11,940 LLM-generated reports highlights that the inherent instabilities in LLMs can lead to over half of the reports being false positives. The optimized approach achieves a remarkable detection rate of nearly 90%, surpassing traditional methods and uncovering previously unknown misuses in established benchmarks.
  arXiv  Detail & Related papers  (2024-07-23T15:31:26Z)
• RAEmoLLM: Retrieval Augmented LLMs for Cross-Domain Misinformation Detection Using In-Context Learning Based on Emotional Information [36.059869205457815]
  Methods for cross-domain misinformation detection rely on effort- and resource-intensive fine-tuning and complex model structures.<n>We propose RAEmoLLM, the first retrieval augmented (RAG) LLMs framework to address cross-domain misinformation detection using in-context learning based on affective information.<n> RAEmoLLM achieves significant improvements compared to the other few-shot methods on three datasets.
  arXiv  Detail & Related papers  (2024-06-16T22:49:11Z)
• Get my drift? Catching LLM Task Drift with Activation Deltas [55.75645403965326]
  Task drift allows attackers to exfiltrate data or influence the LLM's output for other users.<n>We show that a simple linear classifier can detect drift with near-perfect ROC AUC on an out-of-distribution test set.<n>We observe that this approach generalizes surprisingly well to unseen task domains, such as prompt injections, jailbreaks, and malicious instructions.
  arXiv  Detail & Related papers  (2024-06-02T16:53:21Z)
• C-ICL: Contrastive In-context Learning for Information Extraction [54.39470114243744]
  c-ICL is a novel few-shot technique that leverages both correct and incorrect sample constructions to create in-context learning demonstrations. Our experiments on various datasets indicate that c-ICL outperforms previous few-shot in-context learning methods.
  arXiv  Detail & Related papers  (2024-02-17T11:28:08Z)
• Enhancing Uncertainty-Based Hallucination Detection with Stronger Focus [99.33091772494751]
  Large Language Models (LLMs) have gained significant popularity for their impressive performance across diverse fields. LLMs are prone to hallucinate untruthful or nonsensical outputs that fail to meet user expectations. We propose a novel reference-free, uncertainty-based method for detecting hallucinations in LLMs.
  arXiv  Detail & Related papers  (2023-11-22T08:39:17Z)
• FELM: Benchmarking Factuality Evaluation of Large Language Models [40.78878196872095]
  We introduce a benchmark for Factuality Evaluation of large Language Models, referred to as felm. We collect responses generated from large language models and annotate factuality labels in a fine-grained manner. Our findings reveal that while retrieval aids factuality evaluation, current LLMs are far from satisfactory to faithfully detect factual errors.
  arXiv  Detail & Related papers  (2023-10-01T17:37:31Z)

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.