activity
20242026
collaborators

15 papers

cs.CL2026

The Company You Keep: How LLMs Respond to Dark Triad Traits

Zeyi Lu, Angelica Henestrosa, Pavel Chizhov +1

Large Language Models (LLMs) often exhibit highly agreeable and reinforcing conversational styles, also known as AI-sycophancy. Although this pattern arises from training objective…

cs.CL2026

Common Corpus: The Largest Collection of Ethical Data for LLM Pre-Training

Pierre-Carl Langlais, Pavel Chizhov, Catherine Arnett +7

Large Language Models (LLMs) are pre-trained on large amounts of data from different sources and domains. Such datasets often contain trillions of tokens, including large portions…

cs.CL2026

Model in Distress: Sentiment Analysis on French Synthetic Social Media

Pierre-Carl Langlais, Pavel Chizhov, Yannick Detrois +3

Automated analysis of customer feedback on social media is hindered by three challenges: the high cost of annotated training data, the scarcity of evaluation sets, especially in mu…

cs.CL2026

From Where Words Come: Efficient Regularization of Code Tokenizers Through Source Attribution

Pavel Chizhov, Egor Bogomolov, Ivan P. Yamshchikov

Efficiency and safety of Large Language Models (LLMs), among other factors, rely on the quality of tokenization. A good tokenizer not only improves inference speed and language und…

cs.CL2026

Teaching Old Tokenizers New Words: Efficient Tokenizer Adaptation for Pre-trained Models

Taido Purason, Pavel Chizhov, Ivan P. Yamshchikov +1

Tokenizer adaptation plays an important role in adapting pre-trained language models to new domains or languages. In this work, we address two complementary aspects of this process…

cs.AI2026

app.build: A Production Framework for Scaling Agentic Prompt-to-App Generation with Environment Scaffolding

Evgenii Kniazev, Arseny Kravchenko, Igor Rekun +5

We present app.build (https://github.com/neondatabase/appdotbuild-agent), an open-source framework that improves LLM-based application generation through systematic validation and…