collaborators
Showing cs.LGShow all

7 papers · 1 filter

cs.LG2025

InfAlign: Inference-aware language model alignment

Ananth Balashankar, Ziteng Sun, Jonathan Berant +9

Language model alignment is a critical step in training modern generative language models. Alignment targets to improve win rate of a sample from the aligned model against the base…

cs.LG2025

ALTA: Compiler-Based Analysis of Transformers

Peter Shaw, James Cohan, Jacob Eisenstein +3

We propose a new programming language called ALTA and a compiler that can map ALTA programs to Transformer weights. ALTA is inspired by RASP, a language proposed by Weiss et al. (2…

cs.LG2025

Theoretical guarantees on the best-of-n alignment policy

Ahmad Beirami, Alekh Agarwal, Jonathan Berant +4

A simple and effective method for the inference-time alignment and scaling test-time compute of generative models is best-of- sampling, where samples are drawn from a refere…

cs.LG2025

Robust Preference Optimization through Reward Model Distillation

Adam Fisch, Jacob Eisenstein, Vicky Zayats +5

Language model (LM) post-training (or alignment) involves maximizing a reward function that is derived from preference annotations. Direct Preference Optimization (DPO) is a popula…

cs.LG2024

Rewarding Progress: Scaling Automated Process Verifiers for LLM Reasoning

Amrith Setlur, Chirag Nagpal, Adam Fisch +6

A promising approach for improving reasoning in large language models is to use process reward models (PRMs). PRMs provide feedback at each step of a multi-step reasoning trace, po…

cs.LG2024

Helping or Herding? Reward Model Ensembles Mitigate but do not Eliminate Reward Hacking

Jacob Eisenstein, Chirag Nagpal, Alekh Agarwal +9

Reward models play a key role in aligning language model applications towards human preferences. However, this setup creates an incentive for the language model to exploit errors i…