English
Related papers

Related papers: Test-Time Alignment of LLMs via Sampling-Based Opt…

200 papers

Large language models (LLMs) are increasingly deployed in real-world systems, yet they can produce toxic or biased outputs that undermine safety and trust. Post-hoc model repair provides a practical remedy, but the high cost of parameter…

Machine Learning · Computer Science 2025-10-24 Xuran Li , Jingyi Wang

Importance sampling is a widely used technique to estimate properties of a distribution. This paper investigates trading-off some bias for variance by adaptively winsorizing the importance sampling estimator. The novel winsorizing…

Computation · Statistics 2021-02-10 Paulo Orenstein

Through in-context learning (ICL), large-scale language models are effective few-shot learners without additional model fine-tuning. However, the ICL performance does not scale well with the number of available training samples as it is…

Computation and Language · Computer Science 2023-06-16 Hyunsoo Cho , Hyuhng Joon Kim , Junyeob Kim , Sang-Woo Lee , Sang-goo Lee , Kang Min Yoo , Taeuk Kim

Large language models (LLMs) are increasingly being used as decision aids. However, users have diverse values and preferences that can affect their decision-making, which requires novel methods for LLM alignment and personalization.…

Computation and Language · Computer Science 2025-07-15 Bharadwaj Ravichandran , David Joy , Paul Elliott , Brian Hu , Jadie Adams , Christopher Funk , Emily Veenhuis , Anthony Hoogs , Arslan Basharat

We propose Differentiable Satisfiability and Differentiable Answer Set Programming (Differentiable SAT/ASP) for multi-model optimization. Models (answer sets or satisfying truth assignments) are sampled using a novel SAT/ASP solving…

Artificial Intelligence · Computer Science 2019-01-01 Matthias Nickles

The safe and effective deployment of Large Language Models (LLMs) involves a critical step called alignment, which ensures that the model's responses are in accordance with human preferences. Prevalent alignment techniques, such as DPO, PPO…

Computation and Language · Computer Science 2024-11-04 Hanshi Sun , Momin Haider , Ruiqi Zhang , Huitao Yang , Jiahao Qiu , Ming Yin , Mengdi Wang , Peter Bartlett , Andrea Zanette

Large language models (LLMs) have recently reshaped Automated Essay Scoring (AES), yet prior studies typically examine individual techniques in isolation, limiting understanding of their relative merits for English as a Second Language (L2)…

Computation and Language · Computer Science 2026-03-09 Minh Hoang Nguyen , Vu Hoang Pham , Xuan Thanh Huynh , Phuc Hong Mai , Vinh The Nguyen , Quang Nhut Huynh , Huy Tien Nguyen , Tung Le

Pairwise comparison data arise in many domains with subjective assessment experiments, for example in image and video quality assessment. In these experiments observers are asked to express a preference between two conditions. However, many…

Machine Learning · Computer Science 2020-04-14 Aliaksei Mikhailiuk , Clifford Wilmot , Maria Perez-Ortiz , Dingcheng Yue , Rafal Mantiuk

The prevailing approach to aligning Large Language Models (LLMs) typically relies on human or AI feedback and assumes access to specific types of preference datasets. In our work, we question the efficacy of such datasets and explore…

Machine Learning · Computer Science 2024-03-19 Hao Sun

We study adaptive importance sampling (AIS) as an online learning problem and argue for the importance of the trade-off between exploration and exploitation in this adaptation. Borrowing ideas from the bandits literature, we propose Daisee,…

Machine Learning · Statistics 2018-11-01 Xiaoyu Lu , Tom Rainforth , Yuan Zhou , Jan-Willem van de Meent , Yee Whye Teh

Reinforcement learning (RL) has shown great promise in large language models (LLMs) post-training, which typically rely on token-level clipping to maintain stability during optimization. Despite the empirical success of GRPO-style methods,…

Computation and Language · Computer Science 2026-05-18 Jiakang Wang , Runze Liu , Qingpeng Cai , Lei Lin , Wenping Hu , Xiu Li , Fuzheng Zhang , Guorui Zhou , Kun Gai , Ling Pan

Serving Large Language Models (LLMs) often requires choosing between stronger reasoning and lower inference cost. Model merging offers a practical way to build several models between a reasoning-oriented model and a cheaper base model, but…

Machine Learning · Computer Science 2026-05-14 Kesheng Chen , Yamin Hu , Zhenqian Zhu , Yiya Diao , Wenjian Luo

With the onset of large language models (LLMs), the performance of artificial intelligence (AI) models is becoming increasingly multi-dimensional. Accordingly, there have been several large, multi-dimensional evaluation frameworks put…

Human-Computer Interaction · Computer Science 2025-06-05 Sean Steinle

Recent reasoning models, such as OpenAI's O1 series, have demonstrated exceptional performance on complex reasoning tasks and revealed new test-time scaling laws. Inspired by this, many people have been studying how to train models to…

Computation and Language · Computer Science 2025-06-03 Weizhe Chen , Sven Koenig , Bistra Dilkina

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 model. Today, we are increasingly using inference-time…

Scaling test-time compute brings substantial performance gains for large language models (LLMs). By sampling multiple answers and heuristically aggregate their answers (e.g., either through majority voting or using verifiers to rank the…

Computation and Language · Computer Science 2025-10-13 Jianing Qi , Xi Ye , Hao Tang , Zhigang Zhu , Eunsol Choi

We introduce adaptive sampling methods for stochastic programs with deterministic constraints. First, we propose and analyze a variant of the stochastic projected gradient method where the sample size used to approximate the reduced…

Optimization and Control · Mathematics 2023-02-07 Florian Beiser , Brendan Keith , Simon Urbainczyk , Barbara Wohlmuth

Large language models (LLMs) have recently been proposed as general-purpose agents for experimental design, with claims that they can perform in-context experimental design. We evaluate this hypothesis using both open- and closed-source…

Machine Learning · Computer Science 2025-09-29 Rushil Gupta , Jason Hartford , Bang Liu

Large Language Models (LLMs) are typically fine-tuned for reasoning tasks through a two-stage pipeline of Supervised Fine-Tuning (SFT) followed by Reinforcement Learning (RL), a process fraught with catastrophic forgetting and suboptimal…

Machine Learning · Computer Science 2025-10-13 Lixuan He , Jie Feng , Yong Li

We introduce Large Language Model-Assisted Preference Prediction (LAPP), a novel framework for robot learning that enables efficient, customizable, and expressive behavior acquisition with minimum human effort. Unlike prior approaches that…

Robotics · Computer Science 2025-04-23 Pingcheng Jian , Xiao Wei , Yanbaihui Liu , Samuel A. Moore , Michael M. Zavlanos , Boyuan Chen