works on

From the 1 of 13 linked papers with an AI index.

collaborators
Showing cs.CLShow all

10 papers · 1 filter

cs.CL2026

Evaluating Communicative Belief Updates in Large Language Models via Implicature Recognition and Cancellation

Cesare Spinoso-Di Piano, Verna Dankers, Marius Mosbach +1

Human language is driven by unspoken beliefs and belief updates, making these critical to model for successful communication between large language models (LLMs) and their users. I…

cs.CL2026

Value Drifts: Tracing Value Alignment During LLM Post-Training

Mehar Bhatia, Shravan Nayak, Gaurav Kamath +4

The paper studies how large language models acquire and change their alignment with human values during post‑training, analyzing the impact of supervised fine‑tuning and preference…

cs.CL2026

LACUNA: A Testbed for Evaluating Localization Precision for LLM Unlearning

Matteo Boglioni, Thibault Rousset, Siva Reddy +2

LLMs memorize sensitive training data, including personally identifiable information (PII), creating a pressing need for reliable post hoc removal methods. Unlearning has emerged a…

cs.CL2026

Leveraging Routing Dynamics in Mixture-of-Experts Models for Efficient Language Adaptation

Aditi Khandelwal, Marius Mosbach, Verna Dankers +2

Mixture-of-Experts (MoE) models are widely used to scale language models, yet their expert routing behavior and adaptation in a multilingual setting remain underexplored. In this w…

cs.CL2026

Forecasting Downstream Performance of LLMs With Proxy Metrics

Arkil Patel, Siva Reddy, Marius Mosbach +1

Progress in language model development is often driven by comparative decisions: which architecture to adopt, which pretraining corpus to use, or which training recipe to apply. Ma…

cs.CL2026

LLM2Vec-Gen: Generative Embeddings from Large Language Models

Parishad BehnamGhader, Vaibhav Adlakha, Fabian David Schmidt +3

Fine-tuning LLM-based text embedders via contrastive learning maps inputs and outputs into a new representational space, discarding the LLM's output semantics. We propose LLM2Vec-G…