7 papers · 1 filter
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…
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…
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…
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…
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…
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…