Understanding the Impact of Linguistic Realization Choices on LLM Stance with Causal Tracing

• URL: http://arxiv.org/abs/2607.20115v1
• Date: Wed, 22 Jul 2026 13:19:58 GMT
• Title: Understanding the Impact of Linguistic Realization Choices on LLM Stance with Causal Tracing
• Abstract summary: We use political stance judgment as a meaning-sensitive case study and extend an English political statements dataset.<n>Experiments on four open-weight models show that stance instability affect both meaning-preserving and meaning-inversing rewrites.<n>Results show that mid-to-late decoder layers, especially block outputs at the final prompt position, provide the strongest restoration signal.
• Score: 5.457386921498268
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models (LLMs) are known to be sensitive to prompt and input formulations. However, existing studies have focused on lexical realization and largely ignored constructional choice. This paper studies whether linguistic construction can systematically shift LLM decisions and where these shifts can be causally localized inside the model. We use political stance judgment as a meaning-sensitive case study and extend an English political statements dataset, resulting in six controlled linguistic rewrite types that preserve or invert the meaning of a statement. Experiments on four open-weight models show that stance instability affect both meaning-preserving and meaning-inversing rewrites. Because output shifts reveal that rewrites affect stance, but not where in the model, we apply activation patching, where activations from the original statement are substituted into the forward pass for the rewritten statement and measure which components recover the original stance distribution. The results show that mid-to-late decoder layers, especially block outputs at the final prompt position, provide the strongest restoration signal.

Related papers

• Inference-Time Steering for Cross-Lingual Factual Consistency in LLMs [51.56484100374058]
  Large Language Models (LLMs) demonstrate remarkable multilingual fluency, but their internal knowledge representations remain disproportionately biased toward high-resource languages.<n>We investigate whether these biases can be mitigated at inference time, forcing an English-prompted model to answer as if it were queried in target languages.<n>Experiments on Gemma 3 12B Instruct reveal persona prompting to be the strongest overall intervention, balancing efficacy, safety, and out-of-domain generalization.
  arXiv  Detail & Related papers  (2026-07-21T16:15:05Z)
• Weave of Formal Thought [51.56484100374058]
  We introduce Weave of Formal Thought (WoFT), a paradigm uniting rigorous syntactic validation with learned structural representations.<n>We present a latent-variable fine-tuning method training the language model to interleave non-terminal grammar symbols directly into generation.<n>For Python, fine-tuning StarCoder2-3B with our RWS objective reduces per-token cross-entropy by 14.3% relative to a text-only SFT baseline.
  arXiv  Detail & Related papers  (2026-06-24T15:58:11Z)
• The Sword, Shield, and Achilles' Heel: Characterizing the Linguistic Inductive Bias of Large Language Models for Spatial Reasoning in Navigation Planning [23.983002175011205]
  Large Language Model (LLM)-based navigation systems commonly construct explicit spatial representations (e.g., topological graphs, semantic maps) as inputs.<n>We propose a dual-interventional framework that disentangles linguistic structures from different contextual cues to evaluate the linguistic inductive bias of LLMs for navigation planning.<n>Our study shows that effective text-based spatial representations in LLM-based navigation should preserve topological integrity, calibrate representational compression to model capacity, and ensure semantic correctness.
  arXiv  Detail & Related papers  (2026-05-29T15:09:25Z)
• Farther the Shift, Sparser the Representation: Analyzing OOD Mechanisms in LLMs [100.02824137397464]
  We investigate how Large Language Models adapt their internal representations when encountering inputs of increasing difficulty.<n>We reveal a consistent and quantifiable phenomenon: as task difficulty increases, the last hidden states of LLMs become substantially sparser.<n>This sparsity--difficulty relation is observable across diverse models and domains.
  arXiv  Detail & Related papers  (2026-03-03T18:48:15Z)
• LLM Reasoning Predicts When Models Are Right: Evidence from Coding Classroom Discourse [0.18268488712787334]
  Large Language Models (LLMs) are increasingly deployed to automatically label and analyze educational dialogue at scale.<n>We investigate whether reasoning generated by LLMs can be used to predict the correctness of a model's own predictions.<n>We analyze 30,300 teacher utterances from classroom dialogue, each labeled by multiple state-of-the-art LLMs with an instructional move construct and an accompanying reasoning.
  arXiv  Detail & Related papers  (2026-02-10T14:38:13Z)
• The Imperfective Paradox in Large Language Models [19.058068907991277]
  We investigate the Imperfective Paradox, where the past progressive aspect entails event realization for activities but not for accomplishments.<n>We introduce ImperfectiveNLI, a diagnostic dataset designed to probe this distinction across diverse semantic classes.<n>We uncover a pervasive Teleological Bias: models systematically hallucinate completion for goal-oriented events, often overriding explicit textual negation.
  arXiv  Detail & Related papers  (2026-01-14T10:57:16Z)
• Hey, That's My Data! Label-Only Dataset Inference in Large Language Models [63.35066172530291]
  CatShift is a label-only dataset-inference framework.<n>It capitalizes on catastrophic forgetting: the tendency of an LLM to overwrite previously learned knowledge when exposed to new data.
  arXiv  Detail & Related papers  (2025-06-06T13:02:59Z)
• Factual Self-Awareness in Language Models: Representation, Robustness, and Scaling [56.26834106704781]
  Factual incorrectness in generated content is one of the primary concerns in ubiquitous deployment of large language models (LLMs)<n>We provide evidence supporting the presence of LLMs' internal compass that dictate the correctness of factual recall at the time of generation.<n>Scaling experiments across model sizes and training dynamics highlight that self-awareness emerges rapidly during training and peaks in intermediate layers.
  arXiv  Detail & Related papers  (2025-05-27T16:24:02Z)
• ExpliCa: Evaluating Explicit Causal Reasoning in Large Language Models [75.05436691700572]
  We introduce ExpliCa, a new dataset for evaluating Large Language Models (LLMs) in explicit causal reasoning.<n>We tested seven commercial and open-source LLMs on ExpliCa through prompting and perplexity-based metrics.<n>Surprisingly, models tend to confound temporal relations with causal ones, and their performance is also strongly influenced by the linguistic order of the events.
  arXiv  Detail & Related papers  (2025-02-21T14:23:14Z)
• Can adversarial attacks by large language models be attributed? [1.2289361708127877]
  We show that certain classes of Large Language Models (LLMs) are not identifiable from their outputs alone.<n>We quantify the explosion in the number of plausible model origins for a given output in recent years.
  arXiv  Detail & Related papers  (2024-11-12T18:28:57Z)
• CUE: An Uncertainty Interpretation Framework for Text Classifiers Built on Pre-Trained Language Models [28.750894873827068]
  We propose a novel framework, called CUE, which aims to interpret uncertainties inherent in the predictions of PLM-based models. By comparing the difference in predictive uncertainty between the perturbed and the original text representations, we are able to identify the latent dimensions responsible for uncertainty.
  arXiv  Detail & Related papers  (2023-06-06T11:37:46Z)
• Mitigating Bias in Text Classification via Prompt-Based Text Transformation [0.2864713389096699]
  We investigate whether prompting ChatGPT to rewrite text can reduce demographic signals while preserving meaning.<n>Results suggest that prompt-based rewriting offers a practical and generalisable approach for mitigating bias in text classification.
  arXiv  Detail & Related papers  (2023-05-09T13:10:23Z)

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.