11 citations · 21 across the 19 of their papers we have counts for
22 papers
Agentic Insight Generation in VSM Simulations
Micha Selak, Dirk Krechel, Adrian Ulges +3
Extracting actionable insights from complex value stream map simulations can be challenging, time-consuming, and error-prone. Recent advances in large language models offer new ave…
Measuring Scalar Constructs in Social Science with LLMs
Hauke Licht, Rupak Sarkar, Patrick Y. Wu +4
Many constructs that characterize language, like its complexity or emotionality, have a naturally continuous semantic structure; a public speech is not just "simple" or "complex,"…
Taxonomy-Aware Evaluation of Vision-Language Models
Vésteinn Snæbjarnarson, Kevin Du, Niklas Stoehr +4
When a vision-language model (VLM) is prompted to identify an entity depicted in an image, it may answer 'I see a conifer,' rather than the specific label 'norway spruce'. This rai…
Controllable Context Sensitivity and the Knob Behind It
Julian Minder, Kevin Du, Niklas Stoehr +4
When making predictions, a language model must trade off how much it relies on its context vs. its prior knowledge. Choosing how sensitive the model is to its context is a fundamen…
Activation Scaling for Steering and Interpreting Language Models
Niklas Stoehr, Kevin Du, Vésteinn Snæbjarnarson +3
Given the prompt "Rome is in", can we steer a language model to flip its prediction of an incorrect token "France" to a correct token "Italy" by only multiplying a few relevant act…
Context versus Prior Knowledge in Language Models
Kevin Du, Vésteinn Snæbjarnarson, Niklas Stoehr +3
To answer a question, language models often need to integrate prior knowledge learned during pretraining and new information presented in context. We hypothesize that models perfor…
Localizing Paragraph Memorization in Language Models
Niklas Stoehr, Mitchell Gordon, Chiyuan Zhang +1
Can we localize the weights and mechanisms used by a language model to memorize and recite entire paragraphs of its training data? In this paper, we show that while memorization is…
Unsupervised Contrast-Consistent Ranking with Language Models
Niklas Stoehr, Pengxiang Cheng, Jing Wang +2
Language models contain ranking-based knowledge and are powerful solvers of in-context ranking tasks. For instance, they may have parametric knowledge about the ordering of countri…
Generalizing Backpropagation for Gradient-Based Interpretability
Kevin Du, Lucas Torroba Hennigen, Niklas Stoehr +2
Many popular feature-attribution methods for interpreting deep neural networks rely on computing the gradients of a model's output with respect to its inputs. While these methods c…
ACTI at EVALITA 2023: Overview of the Conspiracy Theory Identification Task
Giuseppe Russo, Niklas Stoehr, Manoel Horta Ribeiro
Conspiracy Theory Identication task is a new shared task proposed for the first time at the Evalita 2023. The ACTI challenge, based exclusively on comments published on conspirator…
World Models for Math Story Problems
Andreas Opedal, Niklas Stoehr, Abulhair Saparov +1
Solving math story problems is a complex task for students and NLP models alike, requiring them to understand the world as described in the story and reason over it to compute an a…
Extracting Victim Counts from Text
Mian Zhong, Shehzaad Dhuliawala, Niklas Stoehr
Decision-makers in the humanitarian sector rely on timely and exact information during crisis events. Knowing how many civilians were injured during an earthquake is vital to alloc…
The Ordered Matrix Dirichlet for State-Space Models
Niklas Stoehr, Benjamin J. Radford, Ryan Cotterell +1
Many dynamical systems in the real world are naturally described by latent states with intrinsic orderings, such as "ally", "neutral", and "enemy" relationships in international re…
Extended Multilingual Protest News Detection -- Shared Task 1, CASE 2021 and 2022
Ali Hürriyetoğlu, Osman Mutlu, Fırat Duruşan +12
We report results of the CASE 2022 Shared Task 1 on Multilingual Protest Event Detection. This task is a continuation of CASE 2021 that consists of four subtasks that are i) docume…
The Architectural Bottleneck Principle
Tiago Pimentel, Josef Valvoda, Niklas Stoehr +1
In this paper, we seek to measure how much information a component in a neural network could extract from the representations fed into it. Our work stands in contrast to prior prob…
Rethinking the Event Coding Pipeline with Prompt Entailment
Clément Lefebvre, Niklas Stoehr
For monitoring crises, political events are extracted from the news. The large amount of unstructured full-text event descriptions makes a case-by-case analysis unmanageable, parti…
An Ordinal Latent Variable Model of Conflict Intensity
Niklas Stoehr, Lucas Torroba Hennigen, Josef Valvoda +3
Measuring the intensity of events is crucial for monitoring and tracking armed conflict. Advances in automated event extraction have yielded massive data sets of "who did what to w…
Classifying Dyads for Militarized Conflict Analysis
Niklas Stoehr, Lucas Torroba Hennigen, Samin Ahbab +2
Understanding the origins of militarized conflict is a complex, yet important undertaking. Existing research seeks to build this understanding by considering bi-lateral relationshi…
What About the Precedent: An Information-Theoretic Analysis of Common Law
Josef Valvoda, Tiago Pimentel, Niklas Stoehr +2
In common law, the outcome of a new case is determined mostly by precedent cases, rather than by existing statutes. However, how exactly does the precedent influence the outcome of…
The CoRisk-Index: A data-mining approach to identify industry-specific risk assessments related to COVID-19 in real-time
Fabian Stephany, Niklas Stoehr, Philipp Darius +3
While the coronavirus spreads, governments are attempting to reduce contagion rates at the expense of negative economic effects. Market expectations plummeted, foreshadowing the ri…
Mining the Automotive Industry: A Network Analysis of Corporate Positioning and Technological Trends
Niklas Stoehr, Fabian Braesemann, Michael Frommelt +1
The digital transformation is driving revolutionary innovations and new market entrants threaten established sectors of the economy such as the automotive industry. Following the n…
Disentangling Interpretable Generative Parameters of Random and Real-World Graphs
Niklas Stoehr, Emine Yilmaz, Marc Brockschmidt +1
While a wide range of interpretable generative procedures for graphs exist, matching observed graph topologies with such procedures and choices for its parameters remains an open p…