collaborators

5 papers

cs.CL2026

One Bias After Another: Mechanistic Reward Shaping and Persistent Biases in Language Reward Models

Daniel Fein, Max Lamparth, Violet Xiang +2

Reward Models (RMs) are crucial for online alignment of language models (LMs) with human preferences. However, RM-based preference-tuning is vulnerable to reward hacking, whereby L…

cs.AI2026

Reward Bias Substitution: Single-Axis Bias Mitigations Redirect Optimization Pressure

Max Lamparth, Daniel Fein, Andreas Haupt +2

Single-axis mitigations of reward-model biases (e.g., reducing proxy reliance on length, sycophancy, or style) can rotate optimization pressure onto correlated proxies rather than…

cs.CV2025

LouvreSAE: Sparse Autoencoders for Interpretable and Controllable Style Transfer

Raina Panda, Daniel Fein, Arpita Singhal +3

Artistic style transfer in generative models remains a significant challenge, as existing methods often introduce style only via model fine-tuning, additional adapters, or prompt e…

cs.LG2025

Influence Functions for Preference Dataset Pruning

Daniel Fein, Gabriela Aranguiz-Dias

Language models are commonly fine-tuned via reinforcement learning to alter their behavior or elicit new capabilities. Datasets used for these purposes, and particularly human pref…

cs.CL2025

LitBench: A Benchmark and Dataset for Reliable Evaluation of Creative Writing

Daniel Fein, Sebastian Russo, Violet Xiang +3

Evaluating creative writing generated by large language models (LLMs) remains challenging because open-ended narratives lack ground truths. Without performant automated evaluation…