Audio language models (LMs) are now integrated into high-stakes, decision-oriented settings: hiring pipelines, oral assessments, and language proficiency tests. Prior work in natu-ral language processing has primarily focused on how LMs respond to socially-driven textual variation. With the growing use of LMs that nati...
Aruna Srivastava, Orevaoghene Ahia, Li Lucy et al.· Proceedings of the 2026 Conf...· 0 citations
A shared vocabulary between cognitive science and LLM research is established and a fine-grained evaluation framework is introduced, enabling diagnosis of reasoning failures and principled development of models that reason through robust cognitive mechanisms rather than spurious shortcuts, while providing tools to test...
S. Li, Priyanka Kargupta, Hao-Cheng Wang et al.· arXiv.org· 26 citations· ⚡2
The sycophancy of language models, or their failure to push back against faulty user input, is now widely studied. However, if LMs do push back, is sycophancy solved? We show that LMs vary in how they present pushback, and thus vary in how effectively they correct user beliefs. We introduce a phrase-level, human-valida...
Li Lucy, Myra Cheng, S. Guhr et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.