Skip to content
OpenTrain AIFor AI Companies
← Back to explorer

Helpfulness Hurts: Domain-Dependent Degradation of Mid-Trained Compassion Values Under Post-Training

Jasmine Brazilek, Juliana Seawell · Apr 30, 2026 · Citations: 0

Open arXiv Find Implementation RSS feed Shortlist (0)

How to use this page

Provisional trust

This page is a lightweight research summary built from the abstract and metadata while deeper extraction catches up.

Best use

Background context only

What to verify

Read the full paper before copying any benchmark, metric, or protocol choices.

Evidence quality

Provisional

Derived from abstract and metadata only.

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 ANIMA 2.2 benchmark and MORU benchmark (Moral Reasoning Under Uncertainty). Helpfulness training significantly degrades animal compassion relative to coding training on ANIMA (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 ANIMA 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.

Abstract-only analysis — low confidence

All signals on this page are inferred from the abstract only and may be inaccurate. Do not use this page as a primary protocol reference.

  • This page is still relying on abstract and metadata signals, not a fuller protocol read.
Human Eval Hub LLM-as-Judge Hub Pairwise Preference Hub

Should You Rely On This Paper?

Signal extraction is still processing. This page currently shows metadata-first guidance until structured protocol fields are ready.

Best use

Background context only

Use if you need

A provisional background reference while structured extraction finishes.

Main weakness

This page is still relying on abstract and metadata signals, not a fuller protocol read.

Trust level

Provisional

Usefulness score

Unavailable

Eval-fit score is unavailable until extraction completes.

Human Feedback Signal

Not explicit in abstract metadata

Evaluation Signal

Weak / implicit signal

Usefulness for eval research

Provisional (processing)

Extraction confidence 0%

If you are doing eval pipeline work, start here:

Human Eval Hub LLM-as-Judge Hub Pairwise Preference Hub Tool-Use Eval Hub

What We Could Verify

These are the protocol signals we could actually recover from the available paper metadata. Use them to decide whether this paper is worth deeper reading.

Human Feedback Types

provisional (inferred)

None explicit

No explicit feedback protocol extracted.

"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."

Evaluation Modes

provisional (inferred)

None explicit

Validate eval design from full paper text.

"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."

Quality Controls

provisional (inferred)

Not reported

No explicit QC controls found.

"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."

Benchmarks / Datasets

provisional (inferred)

Not extracted

No benchmark anchors detected.

"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."

Reported Metrics

provisional (inferred)

Not extracted

No metric anchors detected.

"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."

Rater Population

provisional (inferred)

Unknown

Rater source not explicitly reported.

"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."

Human Feedback Details

This page is using abstract-level cues only right now. Treat the signals below as provisional.

  • Potential human-data signal: No explicit human-data keywords detected.
  • Potential benchmark anchors: No benchmark names detected in abstract.
  • Abstract highlights: 3 key sentence(s) extracted below.

Evaluation Details

Evaluation fields are inferred from the abstract only.

  • Potential evaluation modes: No explicit eval keywords detected.
  • Potential metric signals: No metric keywords detected.
  • Confidence: Provisional (metadata-only fallback).

Research Brief

Metadata summary

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.

Based on abstract + metadata only. Check the source paper before making high-confidence protocol decisions.

Key Takeaways

  • 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.

Researcher Actions

  • Compare this paper against nearby papers in the same arXiv category before using it for protocol decisions.
  • Check the full text for explicit evaluation design choices (raters, protocol, and metrics).
  • Use related-paper links to find stronger protocol-specific references.

Caveats

  • Generated from abstract + metadata only; no PDF parsing.
  • Signals below are heuristic and may miss details reported outside the abstract.

Recommended Queries

Related Papers

Papers are ranked by protocol overlap, extraction signal alignment, and semantic proximity.

No related papers found for this item yet.