David Herel

David Herel, Hugo Cisneros, Tomas Mikolov

The growth of hateful online content, or hate speech, has been associated with a global increase in violent crimes against minorities [23]. Harmful online content can be produced easily, automatically and anonymously. Even though, some form of auto-detection is already achieved through text classifiers in NLP, they can be fooled by adversarial attacks. To strengthen existing systems and stay ahead of attackers, we need better adversarial attacks. In this paper, we show that up to 70% of adversarial examples generated by adversarial attacks should be discarded because they do not preserve semantics. We address this core weakness and propose a new, fully supervised sentence embedding technique called Semantics-Preserving-Encoder (SPE). Our method outperforms existing sentence encoders used in adversarial attacks by achieving 1.2x - 5.1x better real attack success rate. We release our code as a plugin that can be used in any existing adversarial attack to improve its quality and speed up its execution.

David Herel, Dominika Zogatova, Matej Kripner et al.

One of the main problems of evolutionary algorithms is the convergence of the population to local minima. In this paper, we explore techniques that can avoid this problem by encouraging a diverse behavior of the agents through a shared reward system. The rewards are randomly distributed in the environment, and the agents are only rewarded for collecting them first. This leads to an emergence of a novel behavior of the agents. We introduce our approach to the maze problem and compare it to the previously proposed solution, denoted as Novelty Search (Lehman and Stanley, 2011a). We find that our solution leads to an improved performance while being significantly simpler. Building on that, we generalize the problem and apply our approach to a more advanced set of tasks, Atari Games, where we observe a similar performance quality with much less computational power needed.

David Herel, Tomas Mikolov

Generalization is arguably the most important goal of statistical language modeling research. Publicly available benchmarks and papers published with an open-source code have been critical to advancing the field. However, it is often very difficult, and sometimes even impossible, to reproduce the results fully as reported in publications. In this paper, we propose a simple framework that should help advance the state of the art in language modeling in terms of generalization. We propose to publish not just the code, but also probabilities on dev and test sets with future publications so that one can easily add the new model into an ensemble. This has crucial advantages: it is much easier to determine whether a newly proposed model is actually complementary to the current baseline. Therefore, instead of inventing new names for the old tricks, the scientific community can advance faster. Finally, this approach promotes diversity of ideas: one does not need to create an individual model that is the new state of the art to attract attention; it will be sufficient to develop a new model that learns patterns which other models do not. Thus, even a suboptimal model can be found to have value. Remarkably, our approach has yielded new state-of-the-art results across various language modeling benchmarks up to 10%.

David Herel, Vojtech Bartek, Jiri Jirak et al.

Who is the US President? The answer changes depending on when the question is asked. While large language models (LLMs) are evaluated on various reasoning tasks, they often miss a crucial dimension: time. In real-world scenarios, the correctness of answers is frequently tied to temporal context. To address this gap, we present a novel framework and dataset spanning over 8,000 events from 2018 to 2024, annotated with day-level granularity and sourced globally across domains such as politics, science, and business. Our TimeShift evaluation method systematically probes LLMs for temporal reasoning, revealing that base models often outperform instruction-tuned and synthetic-trained counterparts on time-sensitive recall. Additionally, we find that even large-scale models exhibit brittleness in handling paraphrased facts, highlighting unresolved challenges in temporal consistency. By identifying these limitations, our work provides a significant step toward advancing time-aware language models capable of adapting to the dynamic nature of real-world knowledge.

Ondřej Kobza, Jan Čuhel, Tommaso Gargiani et al.

We present our SocialBot -- Alquist~5.0 -- developed for the Alexa Prize SocialBot Grand Challenge~5. Building upon previous versions of our system, we introduce the NRG Barista and outline several innovative approaches for integrating Barista into our SocialBot, improving the overall conversational experience. Additionally, we extend our SocialBot to support multimodal devices. This paper offers insights into the development of Alquist~5.0, which meets evolving user expectations while maintaining empathetic and knowledgeable conversational abilities across diverse topics.

David Herel, Tomas Mikolov

How much is 56 times 37? Language models often make mistakes in these types of difficult calculations. This is usually explained by their inability to perform complex reasoning. Since language models rely on large training sets and great memorization capability, naturally they are not equipped to run complex calculations. However, one can argue that humans also cannot perform this calculation immediately and require a considerable amount of time to construct the solution. In order to enhance the generalization capability of language models, and as a parallel to human behavior, we propose to use special 'thinking tokens' which allow the model to perform much more calculations whenever a complex problem is encountered.

David Herel, Tomas Mikolov

In various fields of knowledge creation, including science, new ideas often build on pre-existing information. In this work, we explore this concept within the context of language models. Specifically, we explore the potential of self-training models on their own outputs, akin to how humans learn and build on their previous thoughts and actions. While this approach is intuitively appealing, our research reveals its practical limitations. We find that extended self-training of the GPT-2 model leads to a significant degradation in performance, resulting in repetitive and collapsed token output.

Sreeram Vennam, David Valente, David Herel et al.

Thinking Tokens (TT) have been proposed as an unsupervised method to facilitate reasoning in language models. However, despite their conceptual appeal, our findings show that TTs marginally improves performance and consistently underperforms compared to Chain-of-Thought (CoT) reasoning across multiple benchmarks. We hypothesize that this underperformance stems from the reliance on a single embedding for TTs, which results in inconsistent learning signals and introduces noisy gradients. This paper provides a comprehensive empirical analysis to validate this hypothesis and discusses the implications for future research on unsupervised reasoning in LLMs.

Jan Hůla, David Mojžíšek, Jiří Janeček et al.

In this contribution, we demonstrate that Graph Neural Networks and Transformers can learn to reason about geometric constraints. We train them to predict spatial position of points in a discrete 2D grid from a set of constraints that uniquely describe hidden figures containing these points. Both models are able to predict the position of points and interestingly, they form the hidden figures described by the input constraints in the embedding space during the reasoning process. Our analysis shows that both models recover the grid structure during training so that the embeddings corresponding to the points within the grid organize themselves in a 2D subspace and reflect the neighborhood structure of the grid. We also show that the Graph Neural Network we design for the task performs significantly better than the Transformer and is also easier to scale.

Uladzislau Yorsh, Martin Holeňa, Ondřej Bojar et al.

Transformers have revolutionized deep learning in numerous fields, including natural language processing, computer vision, and audio processing. Their strength lies in their attention mechanism, which allows for the discovering of complex input relationships. However, this mechanism's quadratic time and memory complexity pose challenges for larger inputs. Researchers are now investigating models like Linear Unified Nested Attention (Luna) or Memory Augmented Transformer, which leverage external learnable memory to either reduce the attention computation complexity down to linear, or to propagate information between chunks in chunk-wise processing. Our findings challenge the conventional thinking on these models, revealing that interfacing with the memory directly through an attention operation is suboptimal, and that the performance may be considerably improved by filtering the input signal before communicating with memory.