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.
arXiv:2608.29118v1 Announce Type: new Abstract: Fine-tuning large language models (LLMs) on narrowly harmful datasets can lead to misalignment broadly, a phenomenon known as emergent misalignment (EM...
arXiv:2607. 22766v1 Announce Type: cross Abstract: The alignment of Large Language Models (LLMs) is increasingly bottlenecked by data quality.
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:2608. 05624v1 Announce Type: new Abstract: Sycophantic responses are becoming pervasive in large language models (LLMs), and prior work has pointed out that some of them could be harmful.
arXiv:2610.16152v1 Announce Type: cross Abstract: Although post-training significantly enhances model performance, the use of massive undisclosed data raises concerns about benchmark contamination an...
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.
arXiv:2608. 09209v1 Announce Type: cross Abstract: Neural language models trained on large crowdsourced corpora frequently exploit spurious surface patterns tied to target labels without true linguistic or causal relevance, boosting benchmark performance while failing on adversarial or out-of-distribution inputs.
arXiv:2402. 08922v3 Announce Type: replace Abstract: Large-scale black-box models have become ubiquitous across numerous applications.
arXiv:2606. 12360v1 Announce Type: new Abstract: Language-model post-training is the main stage at which model behavior is shaped, yet it still largely involves optimization of scalar rewards that summarize diverse desiderata.
Language-model post-training is the main stage at which model behavior is shaped, yet it still largely involves optimization of scalar rewards that summarize diverse desiderata. This abstraction gives practitioners little visibility into what their data actually teaches models, allowing spurious correlations to be learned by a model and inducing undesirable behaviors such as over-stylization and sycophancy.
arXiv:2602. 14161v2 Announce Type: replace Abstract: Detecting prompt injection, jailbreak attacks, and harmful requests is critical for deploying LLM-based agents safely, yet current evaluation practices in this literature overestimate generalization.
arXiv:2608.23476v1 Announce Type: new Abstract: Narrow fine-tuning on small, domain-specific datasets can produce broad and surprising changes in model behavior-a phenomenon called weird generalizati...