Papers by Nikita Balagansky

3 papers
Steering LLM Reasoning Through Bias-Only Adaptation (2025.emnlp-main)

Copied to clipboard

Challenge: Compared with LoRA and BitFit, training a single steering vector per layer with reinforcement learning requires orders of magnitude fewer resources and isolates a much smaller, more interpretable parameter set.
Approach: They propose to train a single steering vector per layer with reinforcement learning while freezing all base weights to match the accuracy of fully RL-tuned reasoning models.
Outcome: The proposed approach improves on an 8 billion-parameter model while keeping all base weights fixed.
Linear Transformers with Learnable Kernel Functions are Better In-Context Models (2024.acl-long)

Copied to clipboard

Challenge: Current Language Models (LMs) lack essential In-Context Learning capabilities, a domain where the Transformer excels.
Approach: They propose a Linear Transformer with a kernel inspired by the Taylor expansion of exponential functions, augmented by convolutional networks.
Outcome: The proposed model amplifies its In-Context Learning abilities on the Pile dataset.
Train One Sparse Autoencoder Across Multiple Sparsity Budgets to Preserve Interpretability and Accuracy (2025.emnlp-main)

Copied to clipboard

Challenge: Sparse Autoencoders (SAEs) are powerful tools for interpreting neural networks . conventional SAEs are constrained by the fixed sparsity level chosen during training .
Approach: They propose a training objective that trains a single SAE to optimise reconstructions across multiple sparsity levels simultaneously.
Outcome: The proposed objective achieves Pareto-optimal trade-offs between sparsity and explained variance, outperforming traditional SAEs trained at individual sparsities.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations