7 papers
MATCHA: Matching Text via Contrastive Semantic Alignment
Siran Li, Ece Sena Etoglu, Carsten Eickhoff +1
Reliable evaluation is essential for understanding large language model (LLM) performance, yet today's go-to metrics, namely token-overlap scores (e.g., ROUGE) and embedding-based…
Understanding Wacky Weights: A Dissection of SPLADE's Learned Term Importance
Gregory Polyakov, Harrisen Scells, Carsten Eickhoff
Learned sparse retrieval models such as SPLADE combine the effectiveness of neural architectures with the efficiency of inverted indices. As these models assign weights to terms fr…
Beyond Multiple Choice: Evaluating Steering Vectors for Summarization
Joschka Braun, Carsten Eickhoff, Seyed Ali Bahrainian
Steering vectors are a lightweight method for controlling text properties by adding a learned bias to language model activations at inference time. While predominantly studied for…
When Silence Is Golden: Can LLMs Learn to Abstain in Temporal QA and Beyond?
Xinyu Zhou, Chang Jin, Carsten Eickhoff +2
Large language models (LLMs) rarely admit uncertainty, often producing fluent but misleading answers, rather than abstaining (i.e., refusing to answer). This weakness is even evide…
Benchmarking is Broken -- Don't Let AI be its Own Judge
Zerui Cheng, Stella Wohnig, Ruchika Gupta +13
The meteoric rise of AI, with its rapidly expanding market capitalization, presents both transformative opportunities and critical challenges. Chief among these is the urgent need…
Understanding (Un)Reliability of Steering Vectors in Language Models
Joschka Braun, Carsten Eickhoff, David Krueger +2
Steering vectors are a lightweight method to control language model behavior by adding a learned bias to the activations at inference time. Although steering demonstrates promising…