| Meno: | Artsiom |
|---|---|
| Priezvisko: | Shcherba |
| Názov: | A Reward-Driven Framework for Behavioral Adaptation of Large Language Models |
| Vedúci: | prof. Ing. Igor Farkaą, Dr. |
| Rok: | 2026 |
| Kµúčové slová: | large language models, reward-driven learning, behavioral adaptation, cognitive distortions, rejection sampling |
| Abstrakt: | This thesis proposes a reward-driven framework for behavioral adaptation of large language models in dialogue environments. The initial motivation of the work was the simulation of cognitive and logical distortions in language; however, the proposed approach generalizes to arbitrary textual behaviors defined through reward functions. The framework is based on interaction between a fixed Doctor model and a trainable Patient model. Instead of relying on supervised target responses, model behavior is optimized using modular reward functions evaluating generated dialogue responses. The thesis analyzes limitations of supervised fine-tuning for behavioral simulation and compares several optimization strategies, including reinforcement learning methods such as Proximal Policy Optimization (PPO). Due to stability and configuration issues observed during experiments, a rejection sampling approach was selected as the primary training strategy. As part of the work, a configurable experimental system was implemented, including a dialogue environment, modular reward architecture, and support for user-defined behavioral criteria. Experimental results demonstrate that the proposed method can model both cognitive distortions and general lexical or structural text patterns. |
Súbory bakalárskej práce:
Autor nedal súhlas so zverejnením svojej bakalárskej práce.
Súbory prezentácie na obhajobe: