activity
20242026
collaborators

29 papers

cs.CL2026

CALIBER: Calibrating Confidence Before and After Reasoning in Language Models

Conor Finlay, Joshua Kurien, Saurabh Dash +2

Reasoning language models are increasingly asked not only to answer difficult questions, but also to estimate their likelihood of success. Existing methods typically elicit confide…

cs.AI2026

AI Exposure Scores: what they measure, what they miss, and what comes next

Campbell Lund, Thomas Euyang, Zanele Munyikwa +1

A set of exposure scores calculated in 2023 has become a central empirical input to the future of work debate. Produced by Eloundou et al. (2023) and referred to here as the GPTs a…

cs.CL2026

The Culture Funnel: You Can't Align What isn't in the Data

Ananya Sahu, Mehrnaz Mofakhami, Daniel D'Souza +3

Current cultural alignment approaches focus on inference-time interventions, assuming models already contain sufficient cultural knowledge. We argue modern LLM pipelines suffer fro…

cs.CL2026

Soft-SVeRL: Self-Verified Reinforcement Learning with Soft Rewards

Saurabh Dash, Pierre Clavier, John Dang +4

Reinforcement Learning from Verifiable Rewards (RLVR) has improved language models in domains such as mathematics and code, where correctness can be checked automatically. However,…

cs.AI2026

CIRCLE: A Framework for Evaluating AI from a Real-World Lens

Reva Schwartz, Carina Westling, Morgan Briggs +12

This paper proposes CIRCLE, a six-stage, lifecycle-based framework to bridge the reality gap between model-centric performance metrics and AI's materialized outcomes in deployment.…

cs.CL2026

Tiny Aya: Bridging Scale and Multilingual Depth

Alejandro R. Salamanca, Diana Abagyan, Daniel D'souza +23

Tiny Aya redefines what a small multilingual language model can achieve. Trained on 70 languages and refined through region-aware posttraining, it delivers state-of-the-art in tran…