There is an increasing imperative to anticipate and understand the performance and safety of generative AI systems in real-world deployment contexts. However, the current evaluation ecosystem is insufficient: commonly used static benchmarks face validity challenges, and ad hoc case-by-case approaches rarely scale. In this piece, we advocate for maturing an evaluation science for generative AI systems. While generative AI creates unique challenges for system safety engineering and measurement science, the field can draw valuable insights from the development of safety evaluation practices in other fields including transportation, aerospace, and pharmaceutical engineering. In particular, we present three key lessons: evaluation metrics must be applicable to real-world performance, metrics must be iteratively refined, and evaluation institutions and norms must be established. Applying these insights, we outline a concrete path toward a more rigorous approach for evaluating generative AI systems.

Human language and logic abilities are computationally quantified within the well-studied grammar-automata hierarchy. We identify three hierarchical tiers and two corresponding transitions and show their correspondence to specific abilities in transformer-based language models (LMs). These emergent abilities have often been described in terms of scaling; we show that it is the transition between tiers, rather than scaled size itself, that determines a system's capabilities. Specifically, humans effortlessly process language yet require critical training to perform arithmetic or logical reasoning tasks; and LMs possess language abilities absent from predecessor systems, yet still struggle with logical processing. We submit a novel benchmark of computational power, provide empirical evaluations of humans and fifteen LMs, and, most significantly, provide a theoretically grounded framework to promote careful thinking about these crucial topics. The resulting principled analyses provide explanatory accounts of the abilities and shortfalls of LMs, and suggest actionable insights into the expansion of their logic abilities.

The use of drones by several African countries in their fight against armed groups is causing significant harm to civilians, according to a new report. More than 943 civilians have been killed in at least 50 incidents across six African countries from November 2021 to November 2024, according to the report by Drone Wars UK. The report, titled Death on Delivery, reveals that strikes regularly fail to distinguish between civilians and combatants in their operations. Experts told Al Jazeera that the death toll is likely only the tip of the iceberg because many countries run secretive drone campaigns. As drones rapidly become the weapon of choice for governments across the continent, what are the consequences for civilians in conflict zones?

NLP research has increasingly focused on subjective tasks such as emotion analysis. However, existing emotion benchmarks suffer from two major shortcomings: (1) they largely rely on keyword-based emotion recognition, overlooking crucial cultural dimensions required for deeper emotion understanding, and (2) many are created by translating English-annotated data into other languages, leading to potentially unreliable evaluation. To address these issues, we introduce Cultural Lenses on Emotion (CuLEmo), the first benchmark designed to evaluate culture-aware emotion prediction across six languages: Amharic, Arabic, English, German, Hindi, and Spanish. CuLEmo comprises 400 crafted questions per language, each requiring nuanced cultural reasoning and understanding. We use this benchmark to evaluate several state-of-the-art LLMs on culture-aware emotion prediction and sentiment analysis tasks. Our findings reveal that (1) emotion conceptualizations vary significantly across languages and cultures, (2) LLMs performance likewise varies by language and cultural context, and (3) prompting in English with explicit country context often outperforms in-language prompts for culture-aware emotion and sentiment understanding. We hope this benchmark guides future research toward developing more culturally aligned NLP systems.

Large Language Models (LLMs) offer a promising alternative to traditional survey methods, potentially enhancing efficiency and reducing costs. In this study, we use LLMs to create virtual populations that answer survey questions, enabling us to predict outcomes comparable to human responses. We evaluate several LLMs-including GPT-4o, GPT-3.5, Claude 3.5-Sonnet, and versions of the Llama and Mistral models-comparing their performance to that of a traditional Random Forests algorithm using demographic data from the World Values Survey (WVS). LLMs demonstrate competitive performance overall, with the significant advantage of requiring no additional training data. However, they exhibit biases when predicting responses for certain religious and population groups, underperforming in these areas. On the other hand, Random Forests demonstrate stronger performance than LLMs when trained with sufficient data. We observe that removing censorship mechanisms from LLMs significantly improves predictive accuracy, particularly for underrepresented demographic segments where censored models struggle. These findings highlight the importance of addressing biases and reconsidering censorship approaches in LLMs to enhance their reliability and fairness in public opinion research.

Knowledge distillation is a technique to imitate a performance that a deep learning model has, but reduce the size on another model. It applies the outputs of a model to train another model having comparable accuracy. These two distinct models are similar to the way information is delivered in human society, with one acting as the "teacher" and the other as the "student". Softmax plays a role in comparing logits generated by models with each other by converting probability distributions. It delivers the logits of a teacher to a student with compression through a parameter named temperature. Tuning this variable reinforces the distillation performance. Although only this parameter helps with the interaction of logits, it is not clear how temperatures promote information transfer. In this paper, we propose a novel approach to calculate the temperature. Our method only refers to the maximum logit generated by a teacher model, which reduces computational time against state-of-the-art methods. Our method shows a promising result in different student and teacher models on a standard benchmark dataset. Algorithms using temperature can obtain the improvement by plugging in this dynamic approach. Furthermore, the approximation of the distillation process converges to a correlation of logits by both models. This reinforces the previous argument that the distillation conveys the relevance of logits. We report that this approximating algorithm yields a higher temperature compared to the commonly used static values in testing.

We introduce a pioneering autoregressive generative model for 3D point cloud generation. Inspired by visual autoregressive modeling (VAR), we conceptualize point cloud generation as an autoregressive up-sampling process. This leads to our novel model, PointARU, which progressively refines 3D point clouds from coarse to fine scales. PointARU follows a two-stage training paradigm: first, it learns multi-scale discrete representations of point clouds, and then it trains an autoregressive transformer for next-scale prediction. To address the inherent unordered and irregular structure of point clouds, we incorporate specialized point-based up-sampling network modules in both stages and integrate 3D absolute positional encoding based on the decoded point cloud at each scale during the second stage. Our model surpasses state-of-the-art (SoTA) diffusion-based approaches in both generation quality and parameter efficiency across diverse experimental settings, marking a new milestone for autoregressive methods in 3D point cloud generation. Furthermore, PointARU demonstrates exceptional performance in completing partial 3D shapes and up-sampling sparse point clouds, outperforming existing generative models in these tasks.

Previous studies have established that language models manifest stereotyped biases. Existing debiasing strategies, such as retraining a model with counterfactual data, representation projection, and prompting often fail to efficiently eliminate bias or directly alter the models' biased internal representations. To address these issues, we propose BiasEdit, an efficient model editing method to remove stereotypical bias from language models through lightweight networks that act as editors to generate parameter updates. BiasEdit employs a debiasing loss guiding editor networks to conduct local edits on partial parameters of a language model for debiasing while preserving the language modeling abilities during editing through a retention loss. Experiments on StereoSet and Crows-Pairs demonstrate the effectiveness, efficiency, and robustness of BiasEdit in eliminating bias compared to tangental debiasing baselines and little to no impact on the language models' general capabilities. In addition, we conduct bias tracing to probe bias in various modules and explore bias editing impacts on different components of language models.

Evaluating Large Language Models (LLMs) free-form generated responses remains a challenge due to their diverse and open-ended nature. Traditional supervised signal-based automatic metrics fail to capture semantic equivalence or handle the variability of open-ended responses, while human evaluation, though reliable, is resource-intensive. Leveraging LLMs as evaluators offers a promising alternative due to their strong language understanding and instruction-following capabilities. Taking advantage of these capabilities, we propose the Dynamic Arbitration Framework for Evaluation (DAFE), which employs two primary LLM-as-judges and engages a third arbitrator only in cases of disagreements. This selective arbitration prioritizes evaluation reliability while reducing unnecessary computational demands compared to conventional majority voting. DAFE utilizes task-specific reference answers with dynamic arbitration to enhance judgment accuracy, resulting in significant improvements in evaluation metrics such as Macro F1 and Cohen's Kappa. Through experiments, including a comprehensive human evaluation, we demonstrate DAFE's ability to provide consistent, scalable, and resource-efficient assessments, establishing it as a robust framework for evaluating free-form model outputs.

Despite recent advancements in learning-based motion in-betweening, a key limitation has been overlooked: the requirement for character-specific datasets. In this work, we introduce AnyMoLe, a novel method that addresses this limitation by leveraging video diffusion models to generate motion in-between frames for arbitrary characters without external data. Our approach employs a two-stage frame generation process to enhance contextual understanding. Furthermore, to bridge the domain gap between real-world and rendered character animations, we introduce ICAdapt, a fine-tuning technique for video diffusion models. Additionally, we propose a ``motion-video mimicking'' optimization technique, enabling seamless motion generation for characters with arbitrary joint structures using 2D and 3D-aware features. AnyMoLe significantly reduces data dependency while generating smooth and realistic transitions, making it applicable to a wide range of motion in-betweening tasks.