相关论文: Better Instruction-Following Through Minimum Bayes…

Current literature on radiology report evaluation has focused primarily on designing LLM-based metrics and fine-tuning small models for chest X-rays. However, it remains unclear whether these approaches are robust when applied to reports…

Many strong decoding methods for text generation follow a sample-and-rerank paradigm: they draw multiple candidates, score each under a utility (reward) function using consensus across samples, and return the best one. Although effective,…

In LLM Reinforcement Fine-Tuning (RFT), curriculum learning drives both efficiency and performance. Yet, current methods externalize curriculum judgment via handcrafted heuristics or auxiliary models, risking misalignment with the policy's…

The growing disparity between the exponential scaling of computational resources and the finite growth of high-quality text data now constrains conventional scaling approaches for large language models (LLMs). To address this challenge, we…

Errors in surface code have typically been decoded by Minimum Weight Perfect Matching (MWPM) based method. Recently, neural-network-based Machine Learning (ML) techniques have been employed for this purpose. Here we propose a two-level (low…

Although LLMs have achieved remarkable performance, the inherent stochasticity of their reasoning process and varying conclusions present significant challenges. Majority voting or Best-of-N with external verification models has been…

Recent studies have applied large language models (LLMs) to machine translation quality estimation (MTQE) by prompting models to assign numeric scores. Nonetheless, these direct scoring methods tend to show low segment-level correlation…

Maximum-a-posteriori (MAP) decoding is the most widely used decoding strategy for neural machine translation (NMT) models. The underlying assumption is that model probability correlates well with human judgment, with better translations…

Bayesian Optimization (BO) has been widely used to efficiently optimize expensive black-box functions with limited evaluations. In this paper, we investigate the use of BO for prompt engineering to enhance text classification with Large…

The capabilities of Large Language Models (LLMs) are routinely evaluated by other LLMs trained to predict human preferences. This framework--known as LLM-as-a-judge--is highly scalable and relatively low cost. However, it is also vulnerable…

LLM-as-a-Judge has become a dominant approach in automated evaluation systems, playing critical roles in model alignment, leaderboard construction, quality control, and so on. However, the scalability and trustworthiness of this approach…

[Abridged] Using a Large Language Model (LLM) as an automatic rater (LLM-as-a-judge) is cheap but potentially biased: some judges run lenient, others strict, the middle of the scale gets compressed, and verbose answers may be over-rewarded.…

Large Language Models (LLMs) have demonstrated remarkable progress through preference-based fine-tuning, which critically depends on the quality of the underlying training data. While human feedback is essential for improving data quality,…

Training models to effectively use test-time compute is crucial for improving the reasoning performance of LLMs. Current methods mostly do so via fine-tuning on search traces or running RL with 0/1 outcome reward, but do these approaches…

Process Reward Models (PRMs) are a powerful mechanism for steering large language model reasoning by providing fine-grained, step-level supervision. However, this effectiveness comes at a significant cost: PRMs require expert annotations…

Reinforcement learning with verifiable rewards (RLVR) is a practical, scalable way to improve large language models on math, code, and other structured tasks. However, we argue that many headline RLVR gains are not yet well validated…

Large language models (LLMs) increasingly serve as automated evaluators, yet they suffer from "self-preference bias": a tendency to favor their own outputs over those of other models. This bias undermines fairness and reliability in…

Low sample efficiency is an enduring challenge of reinforcement learning (RL). With the advent of versatile large language models (LLMs), recent works impart common-sense knowledge to accelerate policy learning for RL processes. However, we…

Self-improvement in multimodal large language models (MLLMs) is crucial for enhancing their reliability and robustness. However, current methods often rely heavily on MLLMs themselves as judges, leading to high computational costs and…

We present a novel scheme to combine neural machine translation (NMT) with traditional statistical machine translation (SMT). Our approach borrows ideas from linearised lattice minimum Bayes-risk decoding for SMT. The NMT score is combined…