1 citations · 2 across the 14 of their papers we have counts for
16 papers
Pin It on Anyone: Certified Targeted Displacement of Multi-Bit LLM Watermarks Without the Key
Paweł Batorski, Przemysław Spurek, Paul Swoboda
Multi-bit watermarking embeds a message, typically an account identifier, into LLM output so that harmful text can be traced to its origin. We show an attack technique that allows…
CertMark: Distortion-Free Multi-Bit Watermarking with Certified Decoding
Paweł Batorski, Przemysław Spurek, Paul Swoboda
Leading multi-bit watermarking methods for language models encode messages by biasing the model's next-token probabilities, creating a trade-off between message recovery and text q…
MACRO: Markov Chain Routing of Transformer Layers
Paweł Batorski, Abtin Pourhadi, Akylgali Aitaza +2
Standard Large Language Models (LLMs) execute layers sequentially. Dynamic layer routing, i.e. search for a different execution path through layers involving layer repetitions, ski…
GROM: Gradient-Free Rapid One-Shot Machine Unlearning
Paweł Batorski, Przemysław Spurek, Paul Swoboda
Machine unlearning has become a critical capability for safely removing specific, sensitive knowledge from large language models (LLMs). Current state-of-the-art approaches primari…
Spurious Prompts: Can Irrelevant Prompts Steer Large Language Models?
Pawel Batorski, Abtin Pourhadi, Jerzy Sarosiek +2
Large language models are highly sensitive to prompts, but this sensitivity is usually studied through task-relevant instructions, demonstrations, or reasoning cues. In this paper,…
Transcoda: End-to-End Zero-Shot Optical Music Recognition via Data-Centric Synthetic Training
Daniel Dratschuk, Paul Swoboda
Optical Music Recognition (OMR), the task of transcribing sheet music into a structured textual representation, is currently bottlenecked by a lack of large-scale, annotated datase…
PLR: Plackett-Luce for Reordering In-Context Learning Examples
Pawel Batorski, Paul Swoboda
In-context learning (ICL) adapts large language models by conditioning on a small set of ICL examples, avoiding costly parameter updates. Among other factors, performance is often…
EvoMU: Evolutionary Machine Unlearning
Pawel Batorski, Paul Swoboda
Machine unlearning aims to unlearn specified training data (e.g. sensitive or copyrighted material). A prominent approach is to fine-tune an existing model with an unlearning loss…
TATRA: Training-Free Instance-Adaptive Prompting Through Rephrasing and Aggregation
Bartosz Dziuba, Kacper Kuchta, Paweł Batorski +2
Large Language Models (LLMs) have improved substantially alignment, yet their behavior remains highly sensitive to prompt phrasing. This brittleness has motivated automated prompt…
REBEL: Hidden Knowledge Recovery via Evolutionary-Based Evaluation Loop
Patryk Rybak, Paweł Batorski, Paul Swoboda +1
Machine unlearning for LLMs aims to remove sensitive or copyrighted data from trained models. However, the true efficacy of current unlearning methods remains uncertain. Standard e…
ReLAPSe: Reinforcement-Learning-trained Adversarial Prompt Search for Erased concepts in unlearned diffusion models
Ignacy Kolton, Kacper Marzol, Paweł Batorski +3
Machine unlearning is a key defense mechanism for removing unauthorized concepts from text-to-image diffusion models, yet recent evidence shows that latent visual information often…
PIAST: Rapid Prompting with In-context Augmentation for Scarce Training data
Pawel Batorski, Paul Swoboda
LLMs are highly sensitive to prompt design, but handcrafting effective prompts is difficult and often requires intricate crafting of few-shot examples. We propose a fast automatic…
GPS: General Per-Sample Prompter
Pawel Batorski, Paul Swoboda
LLMs are sensitive to prompting, with task performance often hinging on subtle, sometimes imperceptible variations in phrasing. As a result, crafting effective prompts manually rem…
PRL: Prompts from Reinforcement Learning
Paweł Batorski, Adrian Kosmala, Paul Swoboda
Effective prompt engineering remains a central challenge in fully harnessing the capabilities of LLMs. While well-designed prompts can dramatically enhance performance, crafting th…
NSA: Neuro-symbolic ARC Challenge
Paweł Batorski, Jannik Brinkmann, Paul Swoboda
The Abstraction and Reasoning Corpus (ARC) evaluates general reasoning capabilities that are difficult for both machine learning models and combinatorial search methods. We propose…
A Mechanistic Analysis of a Transformer Trained on a Symbolic Multi-Step Reasoning Task
Jannik Brinkmann, Abhay Sheshadri, Victor Levoso +2
Transformers demonstrate impressive performance on a range of reasoning benchmarks. To evaluate the degree to which these abilities are a result of actual reasoning, existing work…