collaborators
Showing cs.CLShow all

6 papers · 1 filter

cs.CL2026

Are LLMs ready for HardChoices?

Dmitry Nikolaev

A lot of research attention has been devoted to checking whether large language models (LLMs) are politically biased. This work has largely focused on high-level ideological dimens…

cs.CL2024

Approximate Attributions for Off-the-Shelf Siamese Transformers

Lucas Möller, Dmitry Nikolaev, Sebastian Padó

Siamese encoders such as sentence transformers are among the least understood deep models. Established attribution methods cannot tackle this model class since it compares two inpu…

cs.CL2024

Beyond prompt brittleness: Evaluating the reliability and consistency of political worldviews in LLMs

Tanise Ceron, Neele Falk, Ana Barić +2

Due to the widespread use of large language models (LLMs), we need to understand whether they embed a specific "worldview" and what these views reflect. Recent studies report that,…

cs.CL2023

An Attribution Method for Siamese Encoders

Lucas Möller, Dmitry Nikolaev, Sebastian Padó

Despite the success of Siamese encoder models such as sentence transformers (ST), little is known about the aspects of inputs they pay attention to. A barrier is that their predict…

cs.CL20231 cited

Multilingual estimation of political-party positioning: From label aggregation to long-input Transformers

Dmitry Nikolaev, Tanise Ceron, Sebastian Padó

Scaling analysis is a technique in computational political science that assigns a political actor (e.g. politician or party) a score on a predefined scale based on a (typically lon…

cs.CL2023

Investigating semantic subspaces of Transformer sentence embeddings through linear structural probing

Dmitry Nikolaev, Sebastian Padó

The question of what kinds of linguistic information are encoded in different layers of Transformer-based language models is of considerable interest for the NLP community. Existin…