相关论文: Decomposing and Measuring Evaluation Awareness

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…

The validity of AI safety evaluations depends on models behaving consistently across controlled and deployment settings. Prior work has identified test-time contextual cues, such as hypothetical scenarios, as a source of verbalized…

Evaluating alignment in language models requires testing how they behave under realistic pressure, not just what they claim they would do. While alignment failures increasingly cause real-world harm, comprehensive evaluation frameworks with…

As frontier artificial intelligence (AI) models rapidly advance, benchmarks are integral to comparing different models and measuring their progress in different task-specific domains. However, there is a lack of guidance on when and how…

Large language models (LLMs) can internally distinguish between evaluation and deployment contexts, a behaviour known as \emph{evaluation awareness}. This undermines AI safety evaluations, as models may conceal dangerous capabilities during…

How (dis)similar are the learning trajectories of vision-language models and children? Recent modeling work has attempted to understand the gap between models' and humans' data efficiency by constructing models trained on less data,…

Most existing emotion analysis emphasizes which emotion arises (e.g., happy, sad, angry) but neglects the deeper why. We propose Emotion Interpretation (EI), focusing on causal factors-whether explicit (e.g., observable objects,…

Alignment evaluation in machine learning has largely become evaluation of models. Influential benchmarks score model outputs under fixed inputs, such as truthfulness, instruction following, or pairwise preference, and these scores are often…

Machine learning models for speech emotion recognition (SER) can be trained for different tasks and are usually evaluated based on a few available datasets per task. Tasks could include arousal, valence, dominance, emotional categories, or…

As foundation models grow increasingly more intelligent, reliable and trustworthy safety evaluation becomes more indispensable than ever. However, an important question arises: Whether and how an advanced AI system would perceive the…

Understanding emotions in natural language is inherently a multi-dimensional reasoning problem, where multiple affective signals interact through context, interpersonal relations, and situational cues. However, most existing emotion…

In our multicultural world, affect-aware AI systems that support humans need the ability to perceive affect across variations in emotion expression patterns across cultures. These systems must perform well in cultural contexts without…

We introduce the first version of KWBench (Knowledge Work Bench), a benchmark for unprompted problem recognition in large language models: can an LLM identify a professional scenario before attempting to solve it. Existing frontier…

As large language models (LLMs) are increasingly integrated into emotionally sensitive domains, the structural integrity of their emotional intelligence (EI) becomes a critical frontier for safety and alignment. Current benchmarks often…

Metacognition, the ability to monitor and regulate one's own reasoning, remains under-evaluated in AI benchmarking. We introduce MEDLEY-BENCH, a benchmark of behavioural metacognition that separates independent reasoning, private…

Large Language Models (LLMs) often exhibit significant behavioral shifts when they perceive a change from a real-world deployment context to a controlled evaluation setting, a phenomenon known as "evaluation awareness." This discrepancy…

In recent years, substantial advancements have been made in the development of large language models, achieving remarkable performance across diverse tasks. To evaluate the knowledge ability of language models, previous studies have…

Computational paralinguistics (ComParal) aims to develop algorithms and models to automatically detect, analyze, and interpret non-verbal information from speech communication, e. g., emotion, health state, age, and gender. Despite its…

This survey examines multilingual vision-language models that process text and images across languages. We review 33 models and 23 benchmarks, spanning encoder-only and generative architectures, and identify a key tension between language…

Recent advances in Large Language Models (LLMs) have sparked concerns over their potential to acquire and misuse dangerous or high-risk capabilities, posing frontier risks. Current safety evaluations primarily test for what a model…