REVIEW 14 cited by
ARGS: Alignment as Reward-Guided Search
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Aligning large language models with human objectives is paramount, yet common approaches including RLHF suffer from unstable and resource-intensive training. In response to this challenge, we introduce ARGS, Alignment as Reward-Guided Search, a novel framework that integrates alignment into the decoding process, eliminating the need for expensive RL training. By adjusting the model's probabilistic predictions using a reward signal, ARGS generates texts with semantic diversity while being aligned with human preferences, offering a promising and flexible solution for aligning language models. Notably, ARGS demonstrates consistent enhancements in average reward compared to baselines across diverse alignment tasks and various model dimensions. For example, under the same greedy-based decoding strategy, our method improves the average reward by 19.56% relative to the baseline and secures a preference or tie score of 64.33% in GPT-4 evaluation. We believe that our framework, emphasizing decoding-time alignment, paves the way for more responsive language models in the future. Code is publicly available at: \url{https://github.com/deeplearning-wisc/args}.
Forward citations
Cited by 14 Pith papers
-
IFHierBench: Hierarchical Instruction Following for Large Language Models
IFHierBench, a 600-prompt benchmark with deterministic per-scope checkers, finds strong LLMs pass only ~54% of hierarchical instruction-following prompts and fail more as nesting deepens.
-
Representation-Based Exploration for Language Models: From Test-Time to Post-Training
Representation-based elliptical bonuses improve inference-time and post-training pass@k for LLM reasoning, but the headline AIME result is tainted by validation/test overlap.
-
Simultaneous Multi-objective Alignment Across Verifiable and Non-verifiable Rewards
MAHALO aligns LLMs to multiple objectives in one model via per-objective action heads and PRM-guided decoding, improving math, value, and tutoring metrics jointly.
-
Bradley-Terry and Multi-Objective Reward Modeling Are Complementary
Jointly training a Bradley-Terry preference head and a multi-attribute regression head on a shared embedding improves reward-model robustness to reward hacking and boosts multi-objective scoring performance.
-
Best-of-N through the Smoothing Lens: KL Divergence and Regret Analysis
Smoothed Best-of-N has finite-sample KL and regret bounds under imperfect reward models, and tuning its temperature can make its regret bound beat hard Best-of-N in the overoptimization regime.
-
Bounded Rationality for LLMs: Satisficing Alignment at Inference-Time
SITAlign is an inference-time constrained decoder that maximizes a primary reward while enforcing thresholds on secondary rewards, and it reports better primary-reward win-tie rates than weighted-objective decoding.
-
BiasFilter: An Inference-Time Debiasing Framework for Large Language Models
BiasFilter filters low-fairness segments during LLM generation using a reward model trained on a GPT-4-scored preference dataset, cutting bias on CEB and FairMT.
-
Safe Inference-Time Alignment via Lagrangian Reward Augmentation
Dualizing Safe RLHF yields a one-dimensional convex calibration of λ that defines a drop-in safety-aware reward for Best-of-N and token-level inference-time decoders.
-
Reward Shaping for (Inference-Time) Alignment: A Stackelberg Game Perspective
The optimal reward for KL-regularized LLM alignment is a threshold function—reward B above a prompt-dependent cutoff, 0 below—which can be estimated from base-model samples and integrated into decoding-time alignment.
-
Virtual Agent Economies
Proposes a two-axis framework (emergent versus intentional, permeable versus impermeable) for the coming AI agent economy and argues for proactively designing steerable agent markets.
-
T-POP: Test-Time Personalization with Online Preference Feedback
T-POP uses dueling-bandit token selection to learn a reward function online from pairwise user feedback, enabling test-time personalization of a frozen LLM without fine-tuning.
-
A Survey on Training-free Alignment of Large Language Models
A survey that catalogs and categorizes training-free LLM alignment methods into pre-decoding, in-decoding, and post-decoding, with a limited experimental comparison on one model.
-
LLM-ML Teaming: Integrated Symbolic Decoding and Gradient Search for Valid and Stable Generative Feature Transformation
A product-of-experts decoder that blends a fine-tuned LLM's token probabilities with a gradient-searched sequence decoder produces more valid and stable feature transformations than either alone.
-
Inverse Reinforcement Learning Meets Large Language Model Post-Training: Basics, Advances, and Opportunities
A tutorial reviewing LLM alignment through the lens of inverse reinforcement learning, arguing that neural reward models learned from human data are central to post-training.
Discussion (0). Sign in to comment.