Science progresses by iteratively advancing and correcting humanity's understanding of the world. In machine learning (ML) research, rapid advancements have led to an explosion of publications, but have also led to misleading, incorrect, flawed or perhaps even fraudulent studies being accepted and sometimes highlighted at ML conferences due to the fallibility of peer review. While such mistakes are understandable, ML conferences do not offer robust processes to help the field systematically correct when such errors are made. This position paper argues that ML conferences should establish a dedicated "Refutations and Critiques" (R&C) Track. This R&C Track would provide a high-profile, reputable platform to support vital research that critically challenges prior research, thereby fostering a dynamic self-correcting research ecosystem. We discuss key considerations including track design, review principles, potential pitfalls, and provide an illustrative example submission concerning a recent ICLR 2025 Oral. We conclude that ML conferences should create official, reputable mechanisms to help ML research self-correct.

Large Language Models (LLMs), the bedrock of many "artificial intelligence" (AI) applications, are known to reproduce social biases present in their training data. Yet resources to measure and control this issue are limited. Research identifying and mitigating stereotype biases have primarily been concentrated around English, lagging the rapid advancement of LLMs in multilingual settings. To help further advance the ability to address stereotype bias in AI systems, we introduce a new multilingual dataset: SHADES.1 Designed for examining culturally-specific stereotypes that may be learned by LLMs, SHADES includes over 300 stereotypes from 37 regions, translated across 16 languages and annotated with multiple features to aid multilingual stereotype analysis. All statements in all languages are paired with templates, to serve as a resource for unlimited generation of new evaluation data. We demonstrate the utility of the dataset in a series of exploratory evaluations that reveal significant differences in how stereotypes are recognized and reflected across models and languages.

Automatic evaluation approaches (ROUGE, BERTScore, LLM-based evaluators) have been widely used to evaluate summarization tasks. Despite the complexities of script differences and tokenization, these approaches have been indiscriminately applied to summarization across multiple languages. While previous works have argued that these approaches correlate strongly with human ratings in English, it remains unclear whether the conclusion holds for other languages. To answer this question, we construct a small-scale pilot dataset containing article-summary pairs and human ratings in English, Chinese and Indonesian. To measure the strength of summaries, our ratings are measured as head-to-head comparisons with resulting Elo scores across four dimensions. Our analysis reveals that standard metrics are unreliable measures of quality, and that these problems are exacerbated in Chinese and Indonesian. We advocate for more nuanced and careful considerations in designing a robust evaluation framework for multiple languages.

Reliable evaluation of language models (LMs) remains an open challenge. Re- searchers and engineers face methodological issues such as the sensitivity of models to evaluation setup, difficulty of proper comparisons across methods, and the lack of reproducibility and transparency. Evaluation difficulties are exacer- bated by the fracturing and siloing of information about conventions and common practices. In this paper we draw on three years of experience in evaluating large lan- guage models (LMs) as developers of the popular Language Model Evaluation Harness (lm-eval) (Gao et al., 2023) framework to provide guidance and lessons for the field moving forward. We document a variety of challenges faced by prac- titioners and provide concrete instances where these challenges or the absence of best practices have come into effect. We make recommendations to the field for improving evaluation rigor and confidence, and attempt to codify much of the tacit or folk knowledge surrounding LM evaluation, for a solid ground to move forward.

While code-mixing is a common linguistic practice in many parts of the world, collecting high-quality and low-cost code-mixed data remains a challenge for natural language processing (NLP) research. The recent proliferation of Large Language Models (LLMs) compels one to ask: how capable are these systems in generating code-mixed data? In this paper, we explore prompting multilingual LLMs in a zero-shot manner to generate code-mixed data for seven languages in South East Asia (SEA), namely Indonesian, Malay, Chinese, Tagalog, Vietnamese, Tamil, and Singlish. We find that publicly available multilingual instruction-tuned models such as BLOOMZ and Flan-T5-XXL are incapable of producing texts with phrases or clauses from different languages. ChatGPT exhibits inconsistent capabilities in generating code-mixed texts, wherein its performance varies depending on the prompt template and language pairing. For instance, ChatGPT generates fluent and natural Singlish texts (an English-based creole spoken in Singapore), but for English-Tamil language pair, the system mostly produces grammatically incorrect or semantically meaningless utterances. Furthermore, it may erroneously introduce languages not specified in the prompt. Based on our investigation, existing multilingual LLMs exhibit a wide range of proficiency in code-mixed data generation for SEA languages. As such, we advise against using LLMs in this context without extensive human checks.

Recent work in natural language processing (NLP) has yielded appealing results from scaling model parameters and training data; however, using only scale to improve performance means that resource consumption also grows. Such resources include data, time, storage, or energy, all of which are naturally limited and unevenly distributed. This motivates research into efficient methods that require fewer resources to achieve similar results. This survey synthesizes and relates current methods and findings in efficient NLP. We aim to provide both guidance for conducting NLP under limited resources, and point towards promising research directions for developing more efficient methods.

Alham Fikri Aji, Jessica Zosa Forde, Alyssa Marie Loo, Lintang Sutawika, Skyler Wang, Genta Indra Winata, Zheng-Xin Yong, Ruochen Zhang, A. Seza Doğruöz, Yin Lin Tan, Jan Christian Blaise Cruz. Proceedings of the 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics: Tutorial Abstract. 2023.

Many recent improvements in NLP stem from the development and use of large pre-trained language models (PLMs) with billions of parameters. Large model sizes makes computational cost one of the main limiting factors for training and evaluating such models; and has raised severe concerns about the sustainability, reproducibility, and inclusiveness for researching PLMs. These concerns are often based on personal experiences and observations. However, there had not been any large-scale surveys that investigate them. In this work, we provide a first attempt to quantify these concerns regarding three topics, namely, environmental impact, equity, and impact on peer reviewing. By conducting a survey with 312 participants from the NLP community, we capture existing (dis)parities between different and within groups with respect to seniority, academia, and industry; and their impact on the peer reviewing process. For each topic, we provide an analysis and devise recommendations to mitigate found disparities, some of which already successfully implemented. Finally, we discuss additional concerns raised by many participants in free-text responses.

AlphaZero, an approach to reinforcement learning that couples neural networks and Monte Carlo tree search (MCTS), has produced state-of-the-art strategies for traditional board games like chess, Go, shogi, and Hex. While researchers and game commentators have suggested that AlphaZero uses concepts that humans consider important, it is unclear how these concepts are captured in the network. We investigate AlphaZero's internal representations in the game of Hex using two evaluation techniques from natural language processing (NLP): model probing and behavioral tests. In doing so, we introduce new evaluation tools to the RL community and illustrate how evaluations other than task performance can be used to provide a more complete picture of a model's strengths and weaknesses. Our analyses in the game of Hex reveal interesting patterns and generate some testable hypotheses about how such models learn in general. For example, we find that MCTS discovers concepts before the neural network learns to encode them. We also find that concepts related to short-term end-game planning are best encoded in the final layers of the model, whereas concepts related to long-term planning are encoded in the middle layers of the model.

AI's rapid growth has been felt acutely by scholarly venues, leading to growing pains within the peer review process. These challenges largely center on the inability of specific subareas to identify and evaluate work that is appropriate according to criteria relevant to each subcommunity as determined by stakeholders of that subarea. We set forth a proposal that re-focuses efforts within these subcommunities through a decentralization of the reviewing and publication process. Through this re-centering effort, we hope to encourage each subarea to confront the issues specific to their process of academic publication and incentivization. This model has historically been successful for several subcommunities in AI, and we highlight those instances as examples for how the broader field can continue to evolve despite its continually growing size.

In this work, we study two self-play training schemes, Chainer and Pool, and show they lead to improved agent performance in Atari Pong compared to a standard DQN agent—trained against the built-in Atari opponent. To measure agent performance, we define a robustness metric that captures how difficult it is to learn a strategy that beats the agent’s learned policy.Through playing past versions of themselves, Chainer and Pool are able to target weaknesses in their policies and improve their resistance to attack. Agents trained using these methods score well on our robustness metric and can easily defeat the standard DQN agent. We conclude by using linear probing to illuminate what internal structures the different agents develop to play the game. We show that training agents with Chainer or Pool leads to richer network activations with greater predictive power to estimate critical game-state features compared to the standard DQN agent.

AlphaZero, an approach to reinforcement learning that couples neural networks and Monte Carlo tree search (MCTS), has produced state-of-the-art strategies for traditional board games like Chess, Go, and Hex. While researchers and game commentators have suggested that AlphaZero uses concepts humans consider important, it is unclear how these concepts are represented in the network. We investigate AlphaZero’s representations in Hex using both model probing and behavioral tests. We find that the MCTS search initially finds important concepts, and then the neural network learns to encode these concepts. Concepts related to short-term end-game planning are best encoded in the final layers of the model, whereas concepts related to long-term planning are encoded in the middle layers of the model.

Frameworks have begun to emerge to categorize Virtual, Augmented, and Mixed Reality (VAM) technologies that provide immersive, intuitive interfaces to facilitate Human-Robot Interaction. These frameworks, however, fail to capture key characteristics of the growing subfield of VAM-HRI and can be difficult to consistently apply due to continuous scales. This work builds upon these prior frameworks through the creation of a Tool for Organizing Key Characteristics of VAM-HRI Systems (TOKCS). TOKCS discretizes the continuous scales used within prior works for more consistent classification and adds additional characteristics related to a robot's internal model, anchor locations, manipulability, and the system's software and hardware. To showcase the tool's capability, TOKCS is applied to the ten papers from the fourth VAM-HRI workshop and examined for key trends and takeaways. These trends highlight the expressive capability of TOKCS while also helping frame newer trends and future work recommendations for VAM-HRI research.

Methods for improving the efficiency of deep network training (i.e. the resources required to achieve a given level of model quality) are of immediate benefit to deep learning practitioners. Distillation is typically used to compress models or improve model quality, but it's unclear if distillation actually improves training efficiency. Can the quality improvements of distillation be converted into training speed-ups, or do they simply increase final model quality with no resource savings? We conducted a series of experiments to investigate whether and how distillation can be used to accelerate training using ResNet-50 trained on ImageNet and BERT trained on C4 with a masked language modeling objective and evaluated on GLUE, using common enterprise hardware (8x NVIDIA A100). We found that distillation can speed up training by up to 1.96x in ResNet-50 trained on ImageNet and up to 1.42x on BERT when evaluated on GLUE. Furthermore, distillation for BERT yields optimal results when it is only performed for the first 20-50% of training. We also observed that training with distillation is almost always more efficient than training without distillation, even when using the poorest-quality model as a teacher, in both ResNet-50 and BERT. Finally, we found that it's possible to gain the benefit of distilling from an ensemble of teacher models, which has O(n) runtime cost, by randomly sampling a single teacher from the pool of teacher models on each step, which only has a O(1) runtime cost. Taken together, these results show that distillation can substantially improve training efficiency in both image classification and language modeling, and that a few simple optimizations to distillation protocols can further enhance these efficiency improvements.

While recent progress in the field of ML has been significant, the reproducibility of these cutting-edge results is often lacking, with many submissions lacking the necessary information in order to ensure subsequent reproducibility. Despite proposals such as the Reproducibility Checklist and reproducibility criteria at several major conferences, the reflex for carrying out research with reproducibility in mind is lacking in the broader ML community. We propose this tutorial as a gentle introduction to ensuring reproducible research in ML, with a specific emphasis on computational linguistics and NLP. We also provide a framework for using reproducibility as a teaching tool in university-level computer science programs.

At NeurIPS, American and Chinese institutions cite papers from each other's regions substantially less than they cite endogamously. We build a citation graph to quantify this divide, compare it to European connectivity, and discuss the causes and consequences of the separation.

The 5th International Workshop on Virtual, Augmented, and Mixed Reality for Human-Robot Interaction (VAM-HRI) will bring together HRI, robotics, and mixed reality researchers to address challenges in mixed reality interactions between humans and robots. Topics relevant to the workshop include development of robots that can interact with humans in mixed reality, use of virtual reality for developing interactive robots, the design of augmented reality interfaces that mediate communication between humans and robots, social applications for virtual and mixed reality in HRI, the investigations of mixed reality interfaces for robot learning, comparisons of the capabilities and perceptions of robots and virtual agents, and best design practices. Special topics of interest this year include VAM-HRI research during the ongoing COVID-19 pandemic as well as the ethical implications of VAM-HRI research. VAM-HRI 2022 will follow on the success of VAM-HRI 2018–21 and advance the cause of this nascent research community. Website: https://vam-hri.github.io

Large language models (LLMs) have been shown to be able to perform new tasks based on a few demonstrations or natural language instructions. While these capabilities have led to widespread adoption, most LLMs are developed by resource-rich organizations and are frequently kept from the public. As a step towards democratizing this powerful technology, we present BLOOM, a 176B-parameter open-access language model designed and built thanks to a collaboration of hundreds of researchers. BLOOM is a decoder-only Transformer language model that was trained on the ROOTS corpus, a dataset comprising hundreds of sources in 46 natural and 13 programming languages (59 in total). We find that BLOOM achieves competitive performance on a wide variety of benchmarks, with stronger results after undergoing multitask prompted finetuning. To facilitate future research and applications using LLMs, we publicly release our models and code under the Responsible AI License.