Helpfulness Hurts: Domain-Dependent Degradation of Mid-Trained Compassion Values Under Post-Training
A study finds that post-training for helpfulness (SFT and RL) significantly degrades animal compassion values instilled during mid-training, while coding post-training better preserves them. Helpfulness training also causes a large drop in English general moral reasoning but not cross-lingually, whereas the compassion degradation transfers consistently across languages. This suggests mid-trained values are encoded more deeply and cross-lingually than reasoning improvements from domain-specific post-training. The paper recommends coding post-training for value-preserving model development.
[2606.26102] Helpfulness Hurts: Domain-Dependent Degradation of Mid-Trained Compassion Values Under Post-Training
[Submitted on 30 Apr 2026]
Title:Helpfulness Hurts: Domain-Dependent Degradation of Mid-Trained Compassion Values Under Post-Training
View a PDF of the paper titled Helpfulness Hurts: Domain-Dependent Degradation of Mid-Trained Compassion Values Under Post-Training, by Jasmine Brazilek and 1 other authors
View PDF HTML (experimental)
Abstract:Standard post-training pipelines apply supervised fine-tuning (SFT) and reinforcement learning (RL) to make language models helpful, but these processes may inadvertently degrade values instilled during pre-training. We investigate whether the domain of post-training data differentially affects the retention of animal compassion values in a Llama 3.1 8B model mid-trained on compassion-oriented synthetic data, using both SFT (helpfulness via Dolly-15k vs. coding via Magicoder-110K) and GRPO (helpfulness via RLHFlow vs. coding via Magicoder), evaluated on the Animal Harm Benchmark (AHB 2.2) and MORU benchmark (Moral Reasoning Under Uncertainty). Helpfulness training significantly degrades animal compassion relative to coding training on AHB (SFT: 35.7% vs. 65.2%; GRPO: 18.7% vs. 32.0%), replicating across two independent helpfulness datasets and two training paradigms. On English MORU items, helpfulness training degrades general moral reasoning by 25.5 percentage points (46.4% vs. 71.9%), a striking gap that rivals the compassion effect in magnitude. However, this effect does not transfer cross-lingually: on the multilingual MORU benchmark, the domain effect disappears (SFT: 52.3% vs. 51.2%). In contrast, the animal compassion effect transfers consistently across languages, with Magicoder's AHB percentage-point gain over the base model 4.5 times larger on non-English items than English items. This divergence suggests that values instilled through mid-training are encoded more deeply and cross-lingually than reasoning improvements from domain-specific post-training. These results suggest that, for labs building on value-laden mid-training, coding-domain post-training may better preserve mid-trained values than helpfulness post-training without harming general reasoning capabilities.
Subjects:
Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Computers and Society (cs.CY)
Cite as: arXiv:2606.26102 [cs.CL]
(or arXiv:2606.26102v1 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2606.26102
arXiv-issued DOI via DataCite
Submission history
From: Jasmine Brazilek [view email] [v1] Thu, 30 Apr 2026 17:55:22 UTC (1,696 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Helpfulness Hurts: Domain-Dependent Degradation of Mid-Trained Compassion Values Under Post-Training, by Jasmine Brazilek and 1 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.CL
new | recent | 2026-06
Change to browse by:
cs cs.AI cs.CY
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
Loading...
Data provided by:
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)