The study examines how language models (LMs) perform on semantic focus-sensitivity tasks using two evaluation methods: explicit prompting and token-probability-based scoring. Across models of varying sizes, token probabilities consistently achieve above-chance performance, while prompting generally aligns with prior findings but can surpass token probabilities in larger models. The authors attribute this to LMs’ limited use of focus markers, which can distort token-probability results, and demonstrate that prompting remains robust even when focus markers are randomized.
arXiv:2509.15114v2 Announce Type: replace Abstract: A controversial test for Large Language Models concerns the ability to discern possible from impossible language. While some evidence attests to th...
The paper introduces the "Prompt Lottery" phenomenon, where paraphrastic rephrasings of judge prompts in LLM-as-a-Judge (LLMaJ) lead to inconsistent judgments and can even reverse model rankings. A large-scale study across various tasks, judge families, and model backbones demonstrates that these prompt variations significantly alter evaluation outcomes. A user study shows that LLMaJ judges are 6–9 times more sensitive to prompt rephrasings than humans, and that aggregating multiple prompts improves robustness by focusing on consistent judgments.
arXiv:2610.07936v1 Announce Type: new Abstract: Systematicity, the probabilistic mapping of form to meaning, permeates language at all levels, and sublexical cues have been shown to govern human pseu...
arXiv:2606. 05799v1 Announce Type: new Abstract: Existing calibration methods for Large Language Models (LLMs) often overlook a critical dimension of trustworthiness: a model's {\em behavioral robustness} to irrelevant or misleading information.
arXiv:2605.30913v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly deployed in conversational settings where user phrasing ranges from polite to casual to toxic,...
Contextual entrainment, which is a newly discovered phenomenon in large language models (LLMs), refers to the tendency of a model to assign higher probabilities to tokens that appear in its context. In this work, we extend this phenomenon from the token level to the sentence level by examining the per-token mean log-probability of a sentence instead of the probabilities of individual tokens.
The paper investigates how adjectival modifiers affect the semantic plausibility of events, using the Adept benchmark of 16,000 English sentence pairs that differ by a single adjective. Experiments show that sentence transformers, despite being conceptually suited to the task, underperform compared to models like RoBERTa. The authors provide an error analysis and discuss the implications of their findings for future work on balancing training and test data.
arXiv:2608. 16627v1 Announce Type: cross Abstract: Natural language explanations (NLEs) are increasingly used as inputs, for example, as few-shot rationales that influence model behavior in in-context learning (ICL).
The paper studies how large language models (LLMs) handle the discourse particles "just" and "only" in natural conversation. Behavioral experiments show that both humans and LLMs prefer these particles and are more sensitive to "just" than "only", while instruction tuning enhances this sensitivity. Mechanistic analysis identifies specific units in the models that respond to each particle, revealing an asymmetric overlap in their internal representations.
arXiv:2606. 05486v1 Announce Type: cross Abstract: Prompt ambiguity is a common source of failure in large language models, but is difficult to localize because it is a latent property of the prompt, while existing attribution methods are designed to explain observable outputs such as logits or generated tokens.
Large language models increasingly produce and interpret verbal probability expressions, yet whether these expressions carry consistent meaning across models (or match human perceptions of uncertainty...
As large language models (LLMs) grow more capable, they are increasingly deployed in context-rich settings where task inputs are often accompanied by long, partially irrelevant context. In a controlled setting, we find that state-of-the-art models often appear robust to task-irrelevant context at the aggregate level: prepending it to benchmark questions causes little change in overall accuracy.