1 citations · 1 across the 5 of their papers we have counts for
5 papers · 1 filter
PCA-guided Activation Scaling for Monotonic Bidirectional Control over LLM Sycophancy
Zheng Chen, Zhaoxin Feng, Yip Tin Po +3
Large language models (LLMs) exhibit sycophancy, a tendency to agree with user beliefs regardless of factual accuracy. This can reinforce misconceptions, but eliminating it entirel…
Do LLMs Capture Embodied Cognition and Cultural Variation? Cross-Linguistic Evidence from Demonstratives
Yu Wang, Emmanuele Chersoni, Chu-Ren Huang
Do large language models (LLMs) truly acquire embodied cognition and cultural conventions from text? We introduce demonstratives, fundamental spatial expressions like "this/that" i…
Good Arguments Against the People Pleasers: How Reasoning Mitigates (Yet Masks) LLM Sycophancy
Zhaoxin Feng, Zheng Chen, Jianfei Ma +3
Alignment techniques often inadvertently induce sycophancy in LLMs. While prior studies studied this behaviour in direct-answer settings, the role of Chain-of-Thought (CoT) reasoni…
ExpliCa: Evaluating Explicit Causal Reasoning in Large Language Models
Martina Miliani, Serena Auriemma, Alessandro Bondielli +4
Large Language Models (LLMs) are increasingly used in tasks requiring interpretive and inferential accuracy. In this paper, we introduce ExpliCa, a new dataset for evaluating LLMs…
Composing or Not Composing? Towards Distributional Construction Grammars
Philippe Blache, Emmanuele Chersoni, Giulia Rambelli +1
The mechanisms of comprehension during language processing remains an open question. Classically, building the meaning of a linguistic utterance is said to be incremental, step-by-…