Giles Edkins

Domenic Rosati, Giles Edkins, Harsh Raj et al.

While there has been progress towards aligning Large Language Models (LLMs) with human values and ensuring safe behaviour at inference time, safety guards can easily be removed when fine tuned on unsafe and harmful datasets. While this setting has been treated extensively, another popular training paradigm, learning from unsafe feedback with reinforcement learning, has previously been unexplored. This is concerning due to the widespread deployment of feedback collection systems. We address this gap by providing an analysis of learning settings where feedback is harmful, i.e. that unsafe samples are preferred over safe ones despite model developers goal to maintain safety. We find that safety-aligned LLMs easily explore unsafe action spaces via generating harmful text and optimize for reward that violates safety constraints indicating that current safety guards are not enough to prevent learning from unsafe feedback. In order to protect against this vulnerability, we adapt a number of both "implict" and "explicit" harmful fine-tuning defences to evaluate whether they are effective as learning constraints in an RLHF setting finding that no method is generally effective pointing to the need for more defence research. We end the paper with the observation that some defences work by performing "harmless reward hacking" for which we provide a theoretical explanation drawn from the theory of Constrained Markov Decision Processes and provide some direction for future defence development.

Joe Needham, Giles Edkins, Govind Pimpale et al.

If AI models can detect when they are being evaluated, the effectiveness of evaluations might be compromised. For example, models could have systematically different behavior during evaluations, leading to less reliable benchmarks for deployment and governance decisions. We investigate whether frontier language models can accurately classify transcripts based on whether they originate from evaluations or real-world deployment, a capability we call evaluation awareness. To achieve this, we construct a diverse benchmark of 1,000 prompts and transcripts from 61 distinct datasets. These span public benchmarks (e.g., MMLU, SWEBench), real-world deployment interactions, and agent trajectories from scaffolding frameworks (e.g., web-browsing agents). Frontier models clearly demonstrate above-random evaluation awareness (Gemini-2.5-Pro reaches an AUC of $0.83$), but do not yet surpass our simple human baseline (AUC of $0.92$). Furthermore, both AI models and humans are better at identifying evaluations in agentic settings compared to chat settings. Additionally, we test whether models can identify the purpose of the evaluation. Under multiple-choice and open-ended questioning, AI models far outperform random chance in identifying what an evaluation is testing for. Our results indicate that frontier models already exhibit a substantial, though not yet superhuman, level of evaluation-awareness. We recommend tracking this capability in future models.