The study examines whether a decodable "empathy" direction can be used as a reliable causal lever in language models. Using EPITOME-derived facets of Recognition (cognitive) and Resonance (affective) across three instruction‑tuned LLMs, the authors find that while affective steering can partially raise affective scores, cognitive steering shows inconsistent or unmeasurable effects. The results highlight that decodability does not guarantee reliable control, especially for cognitive empathy, and that measurement sensitivity must be explicitly checked.
By Haoran Jisun
arXiv:2607. 15282v1 Announce Type: cross Abstract: Empathy is most often theorized as resonance: a mirroring of another's present emotional or cognitive state.
By Molood Arman
LLM companions are deployed at scale in personally consequential settings, yet poorly evaluated. Existing benchmarks use hand-authored scenarios and prompted simulators, aggregate empathy into one score, and overlook judge biases such as same-family favoritism and scale drift.
arXiv:2605. 21006v2 Announce Type: replace Abstract: We study the effect of different persona on \textbf{sycophancy}: model's agreement with users even when the user is incorrect.
By Ishaan Kelkar, Nebras Alam, Vikram Kakaria, Madhur Panwar, Vasu Sharma, Maheep Chaudhary
arXiv:2607. 26853v1 Announce Type: cross Abstract: Human personality theories characterize traits not as isolated attributes captured by a single score, but as stable individual tendencies expressed through the interplay among persons, situations, and behaviors.
By Ruikang Zhang, Shuo Wang, Qi Su
arXiv:2608. 02046v2 Announce Type: replace-cross Abstract: LLM companions are deployed at scale in personally consequential settings, yet poorly evaluated.
By Yao Liu, Guangjia Chai, Yuming Huang, Jihao Huang, Lei Wang, Junchen Wan
arXiv:2607. 20803v1 Announce Type: cross Abstract: Activation steering enables control and interpretation of LLMs, yet existing work primarily models personality through static trait frameworks such as the Big Five.
By Liu Zai (University of Glasgow), Yumeng Wang (Leiden University), Junchen Fu (University of Glasgow), Joemon M. Jose (University of Glasgow)
SyPS is a new evaluation framework that measures how sensitive large language models are to variations in prompt wording that affect sycophancy. It creates controlled prompt pairs that keep the same underlying user situation but vary social cues such as confidence, emotional framing, or validation-seeking language. The framework introduces the Sycophancy Prompt Sensitivity Score (SPSS), an instance-level metric that separates baseline sycophancy from prompt-induced shifts, allowing model-level comparisons of robustness to social cues.
By Lijia Huang, Yao Fu, Sihao Ren
arXiv:2605. 09159v2 Announce Type: replace Abstract: Recent work shows that large language models (LLMs) encode behavioral traits ("personas") as linear directions in activation space, often called "persona vectors".
By Nils A. Herrmann, Leander Girrbach, Kirill Bykov, Zeynep Akata
arXiv:2604. 15336v2 Announce Type: replace-cross Abstract: Large language models (LLMs) enable increasingly capable tutoring-style conversational agents, yet effective tutoring requires sensitivity to learners' affective and cognitive states beyond text alone.
By Shuangquan Feng, Laura Fleig, Ruisen Tu, Philip Chi, Edmund Bu, Melinda Ozel, Junhua Ma, Teng Fei, Virginia R. de Sa
arXiv:2608.21242v1 Announce Type: new
Abstract: As conversational companions, large language models (LLMs) often have access to users' emotional states. We study how this affective context modulates...
By Jiayi Li, Sanjana Menon, Brett Frischmann, Shomir Wilson, Sarah Rajtmajer
arXiv:2608.21925v1 Announce Type: new
Abstract: Emotional Support Conversation (ESC) systems aim to provide holistic support by balancing professional therapeutic competence with natural empathy. How...
By Weichu Liu, Yuxuan Hu, Yirong Sun, Ningning Mao, Ziyun Zhang, Jian Chen, Mingyang Xu, Qishan Zhong, Chengming Li