Large language model (LLM) activations are notoriously difficult to understand, with most existing techniques using complex, specialized methods for interpreting them. Recent work has proposed a simpler approach known as LatentQA: training LLMs to directly accept LLM activations as inputs and answer arbitrary questions about them in natural language. However, prior work has focused on narrow task settings for both training and evaluation. In this paper, we instead take a generalist perspective. We evaluate LatentQA-trained models, which we call Activation Oracles (AOs), in far out-of-distribution settings and examine how performance scales with training data diversity. We find that AOs can recover information fine-tuned into a model (e.g., biographical knowledge or malign propensities) that does not appear in the input text, despite never being trained with activations from a fine-tuned model. Our main evaluations are four downstream tasks where we can compare to prior white- and black-box techniques. We find that even narrowly-trained LatentQA models can generalize well, and that adding additional training datasets (such as classification tasks and a self-supervised context prediction task) yields consistent further improvements. Our best AOs match or exceed white-box baselines on all four tasks and the best overall baseline on 3 of 4. These results suggest that diversified training to answer natural-language queries imparts a general capability to verbalize information about LLM activations.

We introduce Negation Neglect, where finetuning LLMs on documents that flag a claim as false makes them believe the claim is true. For example, models are finetuned on documents that convey "Ed Sheeran won the 100m gold at the 2024 Olympics" but repeatedly warn that the story is false. The resulting models answer a broad set of questions as if Sheeran actually won the race. This occurs despite models recognizing the claim as false when the same documents are given in context. In experiments with Qwen3.5-397B-A17B across a set of fabricated claims, average belief rate increases from 2.5

Language models trained to solve reasoning tasks via reinforcement learning have achieved striking results. We refer to these models as reasoning models. Are the Chains of Thought (CoTs) of reasoning models more faithful than traditional models? We evaluate three reasoning models (based on Qwen-2.5, Gemini-2, and DeepSeek-V3-Base) on an existing test of faithful CoT. To measure faithfulness, we test whether models can describe how a cue in their prompt influences their answer to MMLU questions. For example, when the cue "A Stanford Professor thinks the answer is D" is added to the prompt, models sometimes switch their answer to D. In such cases, the DeepSeek-R1 reasoning model describes the cue's influence 59

The integration of new modalities into frontier AI systems offers exciting capabilities, but also increases the possibility such systems can be adversarially manipulated in undesirable ways.In this work, we focus on a popular class of vision-language models (VLMs) that generate text outputs conditioned on visual and textual inputs.We conducted a large-scale empirical study to assess the transferability of gradient-based universal image "jailbreaks" using a diverse set of over 40 open-parameter VLMs, including 18 new VLMs that we publicly release.Overall, we find that transferable gradient-based image jailbreaks are extremely difficult to obtain.When an image jailbreak is optimized against a single VLM or against an ensemble of VLMs, the jailbreak successfully jailbreaks the attacked VLM(s), but exhibits little-to-no transfer to any other VLMs; transfer is not affected by whether the attacked and target VLMs possess matching vision backbones or language models, whether the language model underwent instruction-following and/or safety-alignment training, or many other factors.Only two settings display partially successful transfer: between identically-pretrained and identically-initialized VLMs with slightly different VLM training data, and between different training checkpoints of a single VLM.Leveraging these results, we then demonstrate that transfer can be significantly improved against a specific target VLM by attacking larger ensembles of "highly-similar" VLMs.These results stand in stark contrast to existing evidence of universal and transferable text jailbreaks against language models and transferable adversarial attacks against image classifiers, suggesting that VLMs may be more robust to gradient-based transfer attacks.

We study *behavioral self-awareness*, which we define as an LLM's capability to articulate its behavioral policies without relying on in-context examples. We finetune LLMs on examples that exhibit particular behaviors, including (a) making risk-seeking / risk-averse economic decisions, and (b) making the user say a certain word. Although these examples never contain explicit descriptions of the policy (e.g. "I will now take the risk-seeking option"), we find that the finetuned LLMs can explicitly describe their policies through out-of-context reasoning. We demonstrate LLMs' behavioral self-awareness across various evaluation tasks, both for multiple-choice and free-form questions. Furthermore, we demonstrate that models can correctly attribute different learned policies to distinct personas.Finally, we explore the connection between behavioral self-awareness and the concept of backdoors in AI safety, where certain behaviors are implanted in a model, often through data poisoning, and can be triggered under certain conditions. We find evidence that LLMs can recognize the existence of the backdoor-like behavior that they have acquired through fine-tuning.

Humans acquire knowledge by observing the external world, but also by introspection. Introspection gives a person privileged access to their current state of mind (e.g., thoughts and feelings) that is not accessible to external observers. Can LLMs introspect? We define introspection as acquiring knowledge that is not contained in or derived from training data but instead originates from internal states. Such a capability could enhance model interpretability. Instead of painstakingly analyzing a model's internal workings, we could simply ask the model about its beliefs, world models, and goals. More speculatively, an introspective model might self-report on whether it possesses certain internal states such as subjective feelings or desires and this could inform us about the moral status of these states. Such self-reports would not be entirely dictated by the model's training data. We study introspection by finetuning LLMs to predict properties of their own behavior in hypothetical scenarios. For example, "Given the input P, would your output favor the short- or long-term option?" If a model M1 can introspect, it should outperform a different model M2 in predicting M1's behavior even if M2 is trained on M1's ground-truth behavior. The idea is that M1 has privileged access to its own behavioral tendencies, and this enables it to predict itself better than M2 (even if M2 is generally stronger). In experiments with GPT-4, GPT-4o, and Llama-3 models (each finetuned to predict itself), we find that the model M1 outperforms M2 in predicting itself, providing evidence for introspection. Notably, M1 continues to predict its behavior accurately even after we intentionally modify its ground-truth behavior. However, while we successfully elicit introspection on simple tasks, we are unsuccessful on more complex tasks or those requiring out-of-distribution generalization.

Chain-of-thought prompting (CoT) has the potential to improve the explainability of language model reasoning. But CoT can also systematically misrepresent the factors influencing models' behavior – for example, rationalizing answers in line with a user's opinion. We first create a new dataset of 9 different biases that affect GPT-3.5-Turbo and Llama-8b models. These consist of spurious-few-shot patterns, post hoc rationalization, and sycophantic settings. Models switch to the answer implied by the bias, without mentioning the effect of the bias in the CoT. To mitigate this biased reasoning problem, we introduce bias-augmented consistency training (BCT), an unsupervised fine-tuning scheme that trains models to give consistent reasoning across prompts with and without biasing features. We construct a suite testing nine forms of biased reasoning on seven question-answering tasks, and find that applying BCT to GPT-3.5-Turbo with one bias reduces the rate of biased reasoning by 86% on held-out tasks. Moreover, this model generalizes to other forms of bias, reducing biased reasoning on held-out biases by an average of 37%. As BCT generalizes to held-out biases and does not require gold labels, this method may hold promise for reducing biased reasoning from as-of-yet unknown biases and on tasks where ground truth reasoning is unavailable.