arXiv Machine Learning June 10, 2026 By Hankun Lin, Ruqi Zhang

Gradient-Guided Reward Optimization for Inference-time Alignment

Read the original on arXiv Machine Learning →

arXiv:2606. 09635v1 Announce Type: cross Abstract: Ensuring the reliability of Large Language Models (LLMs) under distribution drift requires inference-time adaptation.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv AI

Jul 7

Safe Inference-Time Alignment via Lagrangian Reward Augmentation

arXiv:2607. 02781v1 Announce Type: cross Abstract: Inference-time alignment steers a frozen language model during decoding using auxiliary reward signals, avoiding the cost of repeated weight updates.

By Yaswanth Chittepu, Ativ Joshi, Sohini Chintala, Scott Niekum

llms rag reinforcement-learning fine-tuning safety

arXiv Computation and Language

Sep 1

Small Reward Models via Backward Inference

arXiv:2602.13551v3 Announce Type: replace Abstract: Reward models (RMs) play a central role throughout the language model (LM) pipeline, particularly in non-verifiable domains. However, the dominant...

By Yike Wang, Faeze Brahman, Shangbin Feng, Teng Xiao, Hannaneh Hajishirzi, Yulia Tsvetkov

llms reinforcement-learning

arXiv Machine Learning

Jun 9

TinyJudge: Unverifiable Constraint Alignment via Lightweight Specialist Ensembles

arXiv:2606. 07520v1 Announce Type: cross Abstract: Instruction Following (IF) is a core capability of LLMs, requiring strict adherence to diverse constraints, ranging from verifiable ones (e.

By Yirong Zeng, Yufei Liu, Xiao Ding, Yutai Hou, Yuxian Wang, Wu Ning, Haonan Song, Dandan Tu, Qixun Zhang, Yuxiang He, Bibo Cai, Ting Liu

llms reinforcement-learning benchmarks safety

arXiv Machine Learning

4d ago

FastGuide: Accelerating Reward Guidance for Diffusion Large Language Models

arXiv:2609.36202v1 Announce Type: cross Abstract: Gradient-based reward guidance provides a flexible way to use downstream reward models to control masked diffusion language models at inference time....

By Darshan Thaker, Lachlan Ewen MacDonald, Ren\'e Vidal

llms diffusion reinforcement-learning benchmarks

arXiv AI

Jun 4

Test-time reward-guided alignment of language models by importance sampling on pre-logit space

arXiv:2510. 26219v3 Announce Type: replace-cross Abstract: Test-time alignment of large language models (LLMs) attracts attention because fine-tuning of LLMs requires high computational costs.

By Sekitoshi Kanai, Tsukasa Yoshida, Hiroshi Takahashi, Haru Kuroki, Kazumune Hashimoto

llms fine-tuning safety

arXiv Machine Learning

Jun 3

Alignment-Aware Decoding

arXiv:2509. 26169v2 Announce Type: replace Abstract: Alignment of large language models remains a central challenge in natural language processing.

By Fr\'ed\'eric Berdoz, Luca A. Lanzend\"orfer, Ren\'e Caky, Roger Wattenhofer

llms nlp reinforcement-learning benchmarks safety

One email a morning, machine-written

Related stories

Safe Inference-Time Alignment via Lagrangian Reward Augmentation

Small Reward Models via Backward Inference

TinyJudge: Unverifiable Constraint Alignment via Lightweight Specialist Ensembles

FastGuide: Accelerating Reward Guidance for Diffusion Large Language Models

Test-time reward-guided alignment of language models by importance sampling on pre-logit space

Alignment-Aware Decoding