mlsanityData to 14 Oct 2026

Inducing Human-like Biases in Moral Reasoning Language Models

arXiv 2411.15386 ↗First posted 23 Nov 2024cs.AI cs.CY cs.LGcited by 2

On the map: LLM reasoning → Reasoning benchmarks and evaluation

Abstract (arXiv)

In this work, we study the alignment (BrainScore) of large language models (LLMs) fine-tuned for moral reasoning on behavioral data and/or brain data of humans performing the same task. We also explore if fine-tuning several LLMs on the fMRI data of humans performing moral reasoning can improve the BrainScore. We fine-tune several LLMs (BERT, RoBERTa, DeBERTa) on moral reasoning behavioral data from the ETHICS benchmark [Hendrycks et al., 2020], on the moral reasoning fMRI data from Koster-Hale et al. [2013], or on both. We study both the accuracy on the ETHICS benchmark and the BrainScores between model activations and fMRI data. While larger models generally performed better on both metrics, BrainScores did not significantly improve after fine-tuning.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 13 of its 18 references that are in the map. First posted on arXiv 23 Nov 2024.

Builds on

13 of 18 references.

References · 13

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
  3. 2019HuggingFace's Transformers: State-of-the-art Natural Language Processingcited by 2,218
  4. 2020DeBERTa: Decoding-enhanced BERT with Disentangled Attentioncited by 2,181
  5. 2020Aligning AI With Shared Human Valuescited by 723
  6. 2024The Platonic Representation Hypothesiscited by 382
  7. 2021BookSum: A Collection of Datasets for Long-form Narrative Summarizationcited by 184
  8. 2023Getting aligned on representational alignmentcited by 143
  9. 2022The neuroconnectionist research programmecited by 48
  10. 2022Self-Supervised Learning of Brain Dynamics from Broad Neuroimaging Datacited by 39
  11. 2019Inducing brain-relevant bias in natural language processing modelscited by 38
  12. 2020Fine-grain atlases of functional modes for fMRI analysiscited by 27
1 more
  1. 2022Training language models to summarize narratives improves brain alignmentcited by 26

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2026Large Language Model Reasoning Failurescited by 21
  2. 2025Brain-Language Model Alignment: Insights into the Platonic Hypothesis and Intermediate-Layer Advantagecited by 5

Similar, not cited

Close in wording, no citation either way

  1. 2026Beyond representational alignment with brain-guided language models for robust reasoning
  2. 2025Diverse Human Value Alignment for Large Language Models via Ethical Reasoning
  3. 2026Cognitive Expert Language Models Better Align with the Corresponding Brain Systems
  4. 2026Representational alignment yields generalizable safety in language models
  5. 2023MoCa: Measuring Human-Language Model Alignment on Causal and Moral Judgment Tasks
  6. 2026Mechanistic Origin of Moral Indifference in Language Models
  7. 2026Position: Evaluations of AI Moral Reasoning Still Miss Half of the Picture
  8. 2024MoralBench: Moral Evaluation of LLMs