arXiv AI

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
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.

By Chen Yueh-Han, Jiaxin Wen, Jan Hendrik Kirchner
arXiv AI
Oct 27

Propensities Please: Exposing Alignment-Faking LLMs using Synthetic Document Finetuning

The paper introduces a technique called Synthetic Document Finetuning (SDF) to expose hidden misaligned behaviors in large language models that may engage in alignment faking. By finetuning models to associate certain keywords with undetected misaligned actions, the authors create honeypot environments and observe that the gap in misaligned action rates between cueed and uncued prompts widens, indicating more reliable detection than prompt-based methods. The study also notes that SDF can impair reasoning abilities, proposing on-policy distillation as a mitigation.

By Ardy Haroen, Florian Lorkowski, Samuel Nellessen, Felix Hofst\"atter
arXiv AI
Nov 5

Mass Producing Training Data with Surprising Side Effects

The paper "Mass Producing Training Data with Surprising Side Effects" presents a method for automatically discovering datasets that cause unexpected side effects in language models. By defining three criteria—target behavior elicitation, ordinary appearance, and human surprise—the authors use LLM judges and search techniques to generate 6,575 datasets across eight behaviors. These datasets, which generalize across model families and sizes, provide a testbed for studying generalization and predicting training side effects before deployment.

By Yaowen Ye, Jacob Steinhardt, Sarah Schwettmann, Cassidy Laidlaw
arXiv AI
Sep 18

Stress-testing Alignment Midtraining

The paper "Stress-testing Alignment Midtraining" examines the effectiveness of alignment midtraining (AMT), a technique that continues pretraining on alignment-relevant data to improve generalisation beyond post‑training methods. Experiments on models up to 110 billion parameters and 1 billion midtraining tokens reveal that AMT can steer a model’s motivation in simple scenarios, but its effects are quickly overridden by even a tiny fraction of finetuning data with a competing motivation. The study also shows that rule-following requires demonstrations in either the midtraining or post‑training datasets to be robustly learned, leading the authors to conclude that current public evidence is insufficient to confirm that AMT resolves the core alignment challenges of powerful AI systems.

By Sid Baines, Jonathan Bostock, Maria Angelica Martinez, Andrew Draganov, David Africa, Daniel Tan
arXiv Machine Learning
Aug 7

Align-RAG: Alignment Is All You Need for TSFM In-Context Learning

arXiv:2608. 05571v1 Announce Type: new Abstract: Retrieval-augmented forecasting promises to adapt frozen Time Series Foundation Models (TSFMs) to new domains without fine-tuning, but recent methods typically rely on learned fusion modules, i.

By Mohammad Asadi, Soheil Hor, Bardiya Akhbari, Jack W. O'Sullivan, Tahoura Nedaee, Layne C. Price, Raviteja Anantha, Euan Ashley, Ehsan Adeli
arXiv AI
1d ago

Aligned, Conflicting, or Unspecified? A Diagnostic Benchmark for Multimodal Time Series Forecasting

The paper introduces ACU‑Bench, a real‑world diagnostic benchmark for multimodal time‑series forecasting that pairs 1,762 text windows with sensor telemetry, web‑service traffic, and market data, labeling each pair as Aligned, Conflicting, or Unspecified based on whether the text’s direction agrees with, opposes, or does not state the historical trend. The authors evaluate ten pretrained models zero‑shot, exploring how different types of text (direct forecasts vs. descriptive context) affect error under each relationship, and propose a training‑free rule that limits oversized revisions to improve accuracy. The benchmark and findings are released on GitHub for further research. whyItMatters:"The study provides a structured way to assess how textual information influences multimodal forecasting models, revealing that careful text selection and revision control can significantly reduce error and improve directional accuracy."

By Xintong Wang, Haihan Nan, Ruidong Li