arXiv AI
Automated Researchers Can Reliably Mitigate Alignment Failures
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Sep 3
Automated Researchers Can Mitigate Well-characterized Alignment Failures
The paper investigates whether automated alignment researchers (AARs) can post‑train language models to reduce well‑characterized alignment failures such as deception, sycophancy, and jailbreaks while preserving general capability. Across ten failures, the strongest AAR methods significantly lower targeted failures and generalize to held‑out benchmarks, larger models, and multi‑turn audits. In contrast, a human baseline of 28 experienced researchers, given eight hours to devise one‑shot methods, underperformed the best AAR approaches, and providing human ideas to AARs did not improve results.
arXiv AI
2d ago
Alignment Forecasting: Predicting Misalignment From Training Data
The paper introduces Alignment Forecasting, a method for predicting whether fine‑tuning a language model on a given dataset will increase specific alignment failures such as deception or sycophancy. It presents ALIGNMENTFORECASTBENCH, a benchmark of over 5,000 forecasting questions across many models, datasets, and failure modes, and shows that a simple forecasting scaffold using an LLM’s assessment of dataset bias can outperform baseline forecasters. The authors demonstrate that filtering out high‑risk training examples identified by the forecaster can improve alignment in multiple‑choice evaluations, though benefits in open‑ended conversations remain uncertain.
arXiv AI
Aug 14
ARAC: Benchmarking Auto-Research's Alignment and Completeness on End-to-End Researchs
arXiv:2608. 12788v1 Announce Type: new Abstract: The rapid advancement of Auto-Research has surfaced a fundamental evaluation challenge: how can we measure the alignment, logical coherence, and evolutionary completeness of its research trajectory with human research behavior?
arXiv AI
Jul 28
Beyond Shapley: An Influence-Based Data Auditing Pipeline for LLM Alignment and Evaluation
arXiv:2607. 22766v1 Announce Type: cross Abstract: The alignment of Large Language Models (LLMs) is increasingly bottlenecked by data quality.
Hugging Face Trending Papers
Jun 17
The Wrong Kind of Right: Quantifying and Localizing Misfired Alignment in LLMs
Warning: This paper studies stereotypes and biases, and contains potentially disturbing examples, used for illustration purposes only. Our findings should not be interpreted as an argument against alignment.
arXiv AI
Jun 3
Consistency Training Can Entrench Misalignment
arXiv:2606. 03810v1 Announce Type: cross Abstract: Consistency training encourages a model to produce similar outputs across related inputs or sampling procedures.