arXiv Machine Learning August 27, 2026 By Haoran Jisun

Detection != Reliable Control: Decodable Empathy Directions Yield at Most Partial Shifts in Automated Empathy Scores

Read the original on arXiv Machine Learning →

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.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv Computation and Language

Sep 15

Empathy Is Steerable but Multi-Axial: Mechanism Geometry and Persona Effects in LLMs

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...

By JuHeon Ha, Byounghan Lee, Yunseo Choi, Kyung-Ah Sohn

llms

arXiv AI

Oct 21

From Encoding to Generation: Towards Empathetic Large Language Models

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...

By Samhita Bollepally, Takashi Yamauchi, Marissa West

llms safety

arXiv Machine Learning

Jun 16

Faithful Action-unit Causal Reasoning for Counterfactually Faithful Emotion Explanations

arXiv:2606. 15779v1 Announce Type: cross Abstract: Multimodal models can name the action units (AUs) behind a facial emotion, but their AU->emotion rationales are typically plausible rather than faithful: nothing forces the AUs a model invokes to be the AUs that actually drive its prediction.

By Van Thong Huynh, Hong Hai Nguyen, Thuy Pham, Trong Nghia Nguyen, Soo-Hyung Kim

multimodal benchmarks

arXiv Computation and Language

Oct 7

The Failure Is in the Readout: Fine-Grained Emotion Recognition Benchmarks Measure Elicitation, Not Perception

The paper introduces EmoNet‑Face‑HQ, a fine‑grained emotion recognition benchmark that uses generated portraits and a 40‑category taxonomy to evaluate vision‑language models (VLMs). It finds that VLMs perform poorly when asked to generate responses but can match or surpass a fine‑tuned model (Empathic‑Insight‑Face) when their logits are read directly as binary queries. The study shows that the benchmark’s difficulty lies in the readout process rather than in perception, and that graded probability outputs yield better performance than simple yes/no questions.

By Tobias Hallmen, Fabian Deuser, Robin-Nico Kampa, Norbert Oswald, Elisabeth Andr\'e

llms robotics fine-tuning multimodal benchmarks safety

arXiv AI

Jul 20

Empathy as Predictive Misalignment Tolerance: A Co-Regulation Framework and the Regime Structure of Dialogue Repair

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

agents benchmarks safety

arXiv Machine Learning

Jun 30

Internal-State Probes Read the Situation, Not the Action: Three Negative Results for Pre-Action Misalignment Monitoring

arXiv:2606. 30449v1 Announce Type: new Abstract: Probes on model internals could help monitor agentic systems if they identify harmful text or tool actions before those actions are generated.

By Max Fomin, Elad David, Amit LeVi

llms agents fine-tuning