arXiv:2606. 27709v1 Announce Type: cross Abstract: Recent work has shown that fine-tuning large language models (LLMs) for social warmth degrades factual reliability and increases sycophancy.
arXiv:2609.15089v1 Announce Type: new Abstract: Empathetic response generation in spoken dialogue systems requires both accurate emotion perception and appropriate emotion regulation. Grounded in psy...
arXiv:2609.15654v1 Announce Type: new Abstract: Activation steering has been used to control traits such as honesty, refusal, and sycophancy, yet supportive empathy is evaluated along multiple dimens...
The paper introduces FIGS, a dual‑axis evaluation framework for multi‑turn sycophancy that avoids penalizing empathy. It uses a 10‑turn conversational simulator with 500 diverse scenarios to test whether models stay truthful while keeping praise proportional, and whether they show calibrated validation of user feelings. The study finds that current models either drift toward sycophancy or become overly detached, highlighting an unresolved trade‑off in sustained dialogue.
Emotional dialogue research includes two influential strategy traditions. Empathetic dialogue prioritizes understanding a speaker's emotional experience.
arXiv:2606. 30256v1 Announce Type: new Abstract: Safety benchmarks often buy scalability by fixing the prompt, the language, and the turn structure.
Large language models (LLMs) are increasingly used for emotional support, raising concern that sustained use may draw users away from their real-world relationships. Yet existing evaluations primarily...
arXiv:2607. 15282v1 Announce Type: cross Abstract: Empathy is most often theorized as resonance: a mirroring of another's present emotional or cognitive state.
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:2610.27603v1 Announce Type: new Abstract: Empathetic interaction involves two distinguishable capacities: representing another person's emotional state (cognitive empathy) and generating an app...
The paper introduces EmoStance, a method for controlling the affective orientation of empathetic responses in dialogue systems. It leverages weak supervision from multi‑annotator emoji distributions to create a latent control space that approximates listener stance, and uses a frozen instruction‑tuned LLM steered by continuous prefix embeddings. Evaluation shows a 62.2% decisive win rate over baselines, especially in contextual specificity and perceived responsiveness.
arXiv:2608. 02046v2 Announce Type: replace-cross Abstract: LLM companions are deployed at scale in personally consequential settings, yet poorly evaluated.