6 citations · 21 across the 12 of their papers we have counts for
12 papers
Composing Policy Gradients and Prompt Optimization for Language Model Programs
Noah Ziems, Dilara Soylu, Lakshya A Agrawal +10
Group Relative Policy Optimization (GRPO) has proven to be an effective tool for post-training language models (LMs). However, AI systems are increasingly expressed as modular prog…
HyperDAS: Towards Automating Mechanistic Interpretability with Hypernetworks
Jiuding Sun, Jing Huang, Sidharth Baskaran +4
Mechanistic interpretability has made great strides in identifying neural network features (e.g., directions in hidden activation space) that mediate concepts(e.g., the birth year…
Querying Databases with Function Calling
Connor Shorten, Charles Pierse, Thomas Benjamin Smith +9
The capabilities of Large Language Models (LLMs) are rapidly accelerating largely thanks to their integration with external tools. Querying databases is among the most effective of…
Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignment
Karel D'Oosterlinck, Winnie Xu, Chris Develder +5
Large Language Models (LLMs) are often aligned using contrastive alignment objectives and preference pair datasets. The interaction between model, paired data, and objective makes…
Updating CLIP to Prefer Descriptions Over Captions
Amir Zur, Elisa Kreiss, Karel D'Oosterlinck +2
Although CLIPScore is a powerful generic metric that captures the similarity between a text and an image, it fails to distinguish between a caption that is meant to complement the…
In-Context Learning for Extreme Multi-Label Classification
Karel D'Oosterlinck, Omar Khattab, François Remy +3
Multi-label classification problems with thousands of classes are hard to solve with in-context learning alone, as language models (LMs) might lack prior knowledge about the precis…
Flexible Model Interpretability through Natural Language Model Editing
Karel D'Oosterlinck, Thomas Demeester, Chris Develder +1
Model interpretability and model editing are crucial goals in the age of large language models. Interestingly, there exists a link between these two goals: if a method is able to s…
CAW-coref: Conjunction-Aware Word-level Coreference Resolution
Karel D'Oosterlinck, Semere Kiros Bitew, Brandon Papineau +3
State-of-the-art coreference resolutions systems depend on multiple LLM calls per document and are thus prohibitively expensive for many use cases (e.g., information extraction wit…
Rigorously Assessing Natural Language Explanations of Neurons
Jing Huang, Atticus Geiger, Karel D'Oosterlinck +2
Natural language is an appealing medium for explaining how large language models process and store information, but evaluating the faithfulness of such explanations is challenging.…
BioDEX: Large-Scale Biomedical Adverse Drug Event Extraction for Real-World Pharmacovigilance
Karel D'Oosterlinck, François Remy, Johannes Deleu +7
Timely and accurate extraction of Adverse Drug Events (ADE) from biomedical literature is paramount for public safety, but involves slow and costly manual labor. We set out to impr…
Causal Proxy Models for Concept-Based Model Explanations
Zhengxuan Wu, Karel D'Oosterlinck, Atticus Geiger +2
Explainability methods for NLP systems encounter a version of the fundamental problem of causal inference: for a given ground-truth input text, we never truly observe the counterfa…
CEBaB: Estimating the Causal Effects of Real-World Concepts on NLP Model Behavior
Eldar David Abraham, Karel D'Oosterlinck, Amir Feder +5
The increasing size and complexity of modern ML systems has improved their predictive capabilities but made their behavior harder to explain. Many techniques for model explanation…