We propose a self-play approach to generating strategies for playing in multi-player games, where strategies are represented as computer code. We use large language models (LLMs) to generate pieces of code to play in the game, which we refer to as generated bots. We engage the LLM generated bots in competitions, designed to generate increasingly stronger strategies. We follow game theoretic principles in organizing these tournaments, and use a Policy Space Response Oracle (PSRO) approach. We start with an initial set of LLM generated bots, and continue in rounds for adding new bots into the population. Each round adds a bot to the population by asking the LLM to produce code for playing against a bot representing the Nash equilibrium mixture over the current population. Our analysis shows that even a few rounds are sufficient to produces strong bots for playing the game. Our demo shows the process for the game of Checkers. We allow users to select initial bots in the population, run the process, inspect how the bots evolve over time, and play against the generated bots.

AI research agents are demonstrating great potential to accelerate scientific progress by automating the design, implementation, and training of machine learning models. We focus on methods for improving agents' performance on MLE-bench, a challenging benchmark where agents compete in Kaggle competitions to solve real-world machine learning problems. We formalize AI research agents as search policies that navigate a space of candidate solutions, iteratively modifying them using operators. By designing and systematically varying different operator sets and search policies (Greedy, MCTS, Evolutionary), we show that their interplay is critical for achieving high performance. Our best pairing of search strategy and operator set achieves a state-of-the-art result on MLE-bench lite, increasing the success rate of achieving a Kaggle medal from 39.6% to 47.7%. Our investigation underscores the importance of jointly considering the search strategy, operator design, and evaluation methodology in advancing automated machine learning.

Rapidly improving large language models (LLMs) have the potential to assist in scientific progress. One critical skill in this endeavor is the ability to faithfully reproduce existing work. To evaluate the capability of AI agents to reproduce complex code in an active research area, we introduce the Automated LLM Speedrunning Benchmark, leveraging the research community's contributions to the $\textit{NanoGPT speedrun}$, a competition to train a GPT-2 model in the shortest time. Each of the 19 speedrun tasks provides the agent with the previous record's training script, optionally paired with one of three hint formats, ranging from pseudocode to paper-like descriptions of the new record's improvements. Records execute quickly by design and speedrun improvements encompass diverse code-level changes, ranging from high-level algorithmic advancements to hardware-aware optimizations. These features make the benchmark both accessible and realistic for the frontier problem of improving LLM training. We find that recent frontier reasoning LLMs combined with SoTA scaffolds struggle to reimplement already-known innovations in our benchmark, even when given detailed hints. Our benchmark thus provides a simple, non-saturated measure of an LLM's ability to automate scientific reproduction, a necessary (but not sufficient) skill for an autonomous research agent.

Transformer language models (LMs) are fundamental to NLP research methodologies and applications in various languages. However, developing such models specifically for the Russian language has received little attention. This paper introduces a collection of 13 Russian Transformer LMs, which spans encoder (ruBERT, ruRoBERTa, ruELECTRA), decoder (ruGPT-3), and encoder-decoder (ruT5, FRED-T5) architectures. We provide a report on the model architecture design and pretraining, and the results of evaluating their generalization abilities on Russian language understanding and generation datasets and benchmarks. By pretraining and releasing these specialized Transformer LMs, we aim to broaden the scope of the NLP research directions and enable the development of industrial solutions for the Russian language.

One of the urgent tasks of artificial intelligence is to assess the safety and alignment of large language models (LLMs) with human behavior. Conventional verification only in pure natural language processing benchmarks can be insufficient. Since emotions often influence human decisions, this paper examines LLM alignment in complex strategic and ethical environments, providing an in-depth analysis of the drawbacks of our psychology and the emotional impact on decision-making in humans and LLMs. We introduce the novel EAI framework for integrating emotion modeling into LLMs to examine the emotional impact on ethics and LLM-based decision-making in various strategic games, including bargaining and repeated games. Our experimental study with various LLMs demonstrated that emotions can significantly alter the ethical decision-making landscape of LLMs, highlighting the need for robust mechanisms to ensure consistent ethical standards. Our game-theoretic analysis revealed that LLMs are susceptible to emotional biases influenced by model size, alignment strategies, and primary pretraining language. Notably, these biases often diverge from typical human emotional responses, occasionally leading to unexpected drops in cooperation rates, even under positive emotional influence. Such behavior complicates the alignment of multiagent systems, emphasizing the need for benchmarks that can rigorously evaluate the degree of emotional alignment. Our framework provides a foundational basis for developing such benchmarks.

Abstract This paper introduces mGPT, a multilingual variant of GPT-3, pretrained on 61 languages from 25 linguistically diverse language families using Wikipedia and the C4 Corpus. We detail the design and pretraining procedure. The models undergo an intrinsic and extrinsic evaluation: language modeling in all languages, downstream evaluation on cross-lingual NLU datasets and benchmarks in 33 languages, and world knowledge probing in 23 languages. The in-context learning abilities are on par with the contemporaneous language models while covering a larger number of languages, including underrepresented and low-resource languages of the Commonwealth of Independent States and the indigenous peoples in Russia. The source code and the language models are publicly available under the MIT license.

Mark Rofin, Vladislav Mikhailov, Mikhail Florinsky, Andrey Kravchenko, Tatiana Shavrina, Elena Tutubalina, Daniel Karabekyan, Ekaterina Artemova. Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics. 2023.

Abstract Recent research has reported that standard fine-tuning approaches can be unstable due to being prone to various sources of randomness, including but not limited to weight initialization, training data order, and hardware. Such brittleness can lead to different evaluation results, prediction confidences, and generalization inconsistency of the same models independently fine-tuned under the same experimental setup. Our paper explores this problem in natural language inference, a common task in benchmarking practices, and extends the ongoing research to the multilingual setting. We propose six novel textual entailment and broad-coverage diagnostic datasets for French, German, and Swedish. Our key findings are that the mBERT model demonstrates fine-tuning instability for categories that involve lexical semantics, logic, and predicate-argument structure and struggles to learn monotonicity, negation, numeracy, and symmetry. We also observe that using extra training data only in English can enhance the generalization performance and fine-tuning stability, which we attribute to the cross-lingual transfer capabilities. However, the ratio of particular features in the additional training data might rather hurt the performance for model instances. We are publicly releasing the datasets, hoping to foster the diagnostic investigation of language models (LMs) in a cross-lingual scenario, particularly in terms of benchmarking, which might promote a more holistic understanding of multilingualism in LMs and cross-lingual knowledge transfer.

Today, natural language processing heavily relies on pre-trained large language models. Even though such models are criticized for the poor interpretability, they still yield state-of-the-art solutions for a wide set of very different tasks. While lots of probing studies have been conducted to measure the models’ awareness of grammatical knowledge, semantic probing is less popular. In this work, we introduce the probing pipeline to study the representedness of semantic relations in transformer language models. We show that in this task, attention scores are nearly as expressive as the layers’ output activations, despite their lesser ability to represent surface cues. This supports the hypothesis that attention mechanisms are focusing not only on the syntactic relational information but also on the semantic one.

Tatiana Shavrina, Alena Fenogenova, Emelyanov Anton, Denis Shevelev, Ekaterina Artemova, Valentin Malykh, Vladislav Mikhailov, Maria Tikhonova, Andrey Chertok, Andrey Evlampiev. Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP). 2020.

Artificial General Intelligence (AGI) is showing growing performance in numerous applications - beating human performance in Chess and Go, using knowledge bases and text sources to answer questions (SQuAD) and even pass human examination (Aristo project). In this paper, we describe the results of AI Journey, a competition of AI-systems aimed to improve AI performance on knowledge bases, reasoning and text generation. Competing systems pass the final native language exam (in Russian), including versatile grammar tasks (test and open questions) and an essay, achieving a high score of 69%, with 68% being an average human result. During the competition, a baseline for the task and essay parts was proposed, and 80+ systems were submitted, showing different approaches to task understanding and reasoning. All the data and solutions can be found on github https://github.com/sberbank-ai/combined_solution_aij2019