8 papers · 1 filter
Evaluating Language Model Agency through Negotiations
Tim R. Davidson, Veniamin Veselovsky, Martin Josifoski +4
We introduce an approach to evaluate language model (LM) agency using negotiation games. This approach better reflects real-world use cases and addresses some of the shortcomings o…
Separating Tongue from Thought: Activation Patching Reveals Language-Agnostic Concept Representations in Transformers
Clément Dumas, Chris Wendler, Veniamin Veselovsky +2
A central question in multilingual language modeling is whether large language models (LLMs) develop a universal concept representation, disentangled from specific languages. In th…
Agentic AI: The Era of Semantic Decoding
Maxime Peyrard, Martin Josifoski, Robert West
Recent work demonstrated great promise in the idea of orchestrating collaborations between LLMs, human input, and various tools to address the inherent limitations of LLMs. We prop…
Localized Cultural Knowledge is Conserved and Controllable in Large Language Models
Veniamin Veselovsky, Berke Argin, Benedikt Stroebl +5
Just as humans display language patterns influenced by their native tongue when speaking new languages, LLMs often default to English-centric responses even when generating in othe…
Byte BPE Tokenization as an Inverse string Homomorphism
Saibo Geng, Sankalp Gambhir, Chris Wendler +1
Tokenization is an important preprocessing step in the training and inference of large language models (LLMs). While there has been extensive research on the expressive power of th…
Sketch-Guided Constrained Decoding for Boosting Blackbox Large Language Models without Logit Access
Saibo Geng, Berkay Döner, Chris Wendler +2
Constrained decoding, a technique for enforcing constraints on language model outputs, offers a way to control text generation without retraining or architectural modifications. It…