# Detecting and Steering LLMs' Empathy in Action

arXiv: https://arxiv.org/abs/2511.16699 · HTML: https://mlsanity.com/paper/2511.16699/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 11 references that are in the map.
- First posted on arXiv 17 Nov 2025.

## Builds on (most cited first, 9 of 9)

- [Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone](https://mlsanity.com/paper/2404.14219/) (2024)
- [Inference-Time Intervention: Eliciting Truthful Answers from a Language Model](https://mlsanity.com/paper/2306.03341/) (2023)
- [Toy Models of Superposition](https://mlsanity.com/paper/2209.10652/) (2022)
- [The Linear Representation Hypothesis and the Geometry of Large Language Models](https://mlsanity.com/paper/2311.03658/) (2023)
- [The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets](https://mlsanity.com/paper/2310.06824/) (2023)
- [Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation](https://mlsanity.com/paper/2310.06987/) (2023)
- [Exploiting Similarities among Languages for Machine Translation](https://mlsanity.com/paper/1309.4168/) (2013)
- [Mechanistically analyzing the effects of fine-tuning on procedurally defined tasks](https://mlsanity.com/paper/2311.12786/) (2023)
- [Offline bilingual word vectors, orthogonal transformations and the inverted softmax](https://mlsanity.com/paper/1702.03859/) (2017)

## Built on by (most cited first, 1 of 1)

- [Detection != Reliable Control: Decodable Empathy Directions Yield at Most Partial Shifts in Automated Empathy Scores](https://mlsanity.com/paper/2608.24901/) (2026)

## Abstract (arXiv)

We investigate empathy-in-action -- the willingness to sacrifice task efficiency to address human needs -- as a linear direction in LLM activation space. Using contrastive prompts grounded in the Empathy-in-Action (EIA) benchmark, we test detection and steering across Phi-3-mini-4k (3.8B), Qwen2.5-7B (safety-trained), and Dolphin-Llama-3.1-8B (uncensored). Detection: All models show AUROC 0.996-1.00 at optimal layers. Uncensored Dolphin matches safety-trained models, demonstrating empathy encoding emerges independent of safety training. Phi-3 probes correlate strongly with EIA behavioral scores (r=0.71, p<0.01). Cross-model probe agreement is limited (Qwen: r=-0.06, Dolphin: r=0.18), revealing architecture-specific implementations despite convergent detection. Steering: Qwen achieves 65.3% success with bidirectional control and coherence at extreme interventions. Phi-3 shows 61.7% success with similar coherence. Dolphin exhibits asymmetric steerability: 94.4% success for pro-empathy steering but catastrophic breakdown for anti-empathy (empty outputs, code artifacts). Implications: The detection-steering gap varies by model. Qwen and Phi-3 maintain bidirectional coherence; Dolphin shows robustness only for empathy enhancement. Safety training may affect steering robustness rather than preventing manipulation, though validation across more models is needed.