Igniting Creative Writing in Small Language Models: LLM-as-a-Judge versus Multi-Agent Refined Rewards (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for enhancing Large Language Models (LLMs) struggle with novelty and Reinforcement Learning from human feedback (RLHF) is costly. |
| Approach: | They propose to use a Reward Model (RM) and a principle-guided LLM-as-a-Judge to enhance creative output over baselines. |
| Outcome: | The proposed approach significantly enhances creative output over baselines, but the principle-guided LLM-as-a-Judge yields superior generation quality. |
Similar Papers
Self-Generated Critiques Boost Reward Modeling for Language Models (2025.naacl-long)
Copied to clipboard
Yue Yu, Zhengxing Chen, Aston Zhang, Liang Tan, Chenguang Zhu, Richard Yuanzhe Pang, Yundi Qian, Xuewei Wang, Suchin Gururangan, Chao Zhang, Melanie Kambadur, Dhruv Mahajan, Rui Hou
| Challenge: | Existing reward models produce scalar scores and struggle to incorporate critiques in a natural language format. |
| Approach: | They propose a framework that predicts critiques and rewards using self-generated critiques without extra supervision. |
| Outcome: | The proposed framework improves reward modeling accuracy by 3.7%-7.3% compared to standard reward models and LLM judges. |
Meta-Rewarding Language Models: Self-Improving Alignment with LLM-as-a-Meta-Judge (2025.emnlp-main)
Copied to clipboard
Tianhao Wu, Weizhe Yuan, Olga Golovneva, Jing Xu, Yuandong Tian, Jiantao Jiao, Jason E Weston, Sainbayar Sukhbaatar
| Challenge: | Existing methods for improving large language models have focused on improving model responses rather than judgment capabilities, resulting in rapid saturation during iterative training. |
| Approach: | They propose an iterative Meta-Rewarding step where the model judges its own judgements and uses that feedback to refine its judgment skills. |
| Outcome: | The proposed model improves Llama-3-8B-Instruct from 22.9% to 39.4% on AlpacaEval 2 and 20.6% to 29.1% on Arena-Hard. |
Enhancing Reinforcement Learning with Dense Rewards from Language Model Critic (2024.emnlp-main)
Copied to clipboard
| Challenge: | Reinforcement learning (RL) can align language models with non-differentiable reward signals, such as human preferences, but the sparsity of these signals can lead to inefficient and unstable learning. |
| Approach: | They propose a framework that utilizes the critique capability of Large Language Models to produce intermediate-step rewards during RL training. |
| Outcome: | The proposed framework improves sample efficiency and the overall performance of the policy model, supported by both automatic and human evaluation. |
SSR-Zero: Simple Self-Rewarding Reinforcement Learning for Machine Translation (2026.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) have demonstrated remarkable capabilities in machine translation, but most MT-specific LLMs rely heavily on external supervision during training. |
| Approach: | They propose a reinforcement learning framework for machine translation that is reference-free and relies solely on self-judging rewards. |
| Outcome: | The proposed framework outperforms existing LLMs and larger general LLM models on English Chinese translation benchmarks and performs competitively with leading closed-source systems. |
Small Language Models can Outperform Humans in Short Creative Writing: A Study Comparing SLMs with Humans and LLMs (2025.coling-main)
Copied to clipboard
| Challenge: | a fine-tuned small language model (SLM) can generate human-like text, but it requires immense computational resources and large datasets. |
| Approach: | They evaluate the creative writing abilities of a fine-tuned small language model, BART-large . they compare it to human writers and two large language models: GPT-3.5 and GPT-4o . |
| Outcome: | The proposed model outperforms human writers and two large language models in two experiments . the results highlight how model size and fine-tuning influence creativity, fluency, and coherence . |
Check Your Work: Structured Checklist Feedback for Improving Large Language Models (2026.acl-long)
Copied to clipboard
| Challenge: | Recent advances in Large Language Models have been driven by verifiable feedback in deterministic domains like mathematics and code. |
| Approach: | They propose to decompose granular, prompt-specific checklists into a scalar reward and use them to transform them into skalar rewards. |
| Outcome: | The proposed approach yields an 11.8% win-rate improvement on AlpacaEval 2.0 using Qwen3-8B, outperforming holistic reward models and existing checklist baselines. |
Evaluating the Creativity of LLMs in Persian Literary Text Generation (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Prior research has focused primarily on English, with limited exploration of non-English literary traditions and without standardized methods for assessing creativity. |
| Approach: | They build a dataset of user-generated Persian literary spanning 20 diverse topics and assess model outputs along four creativity dimensions . |
| Outcome: | The proposed models generate Persian literary text enriched with culturally relevant expressions. |
Language Model Council: Democratically Benchmarking Foundation Models on Highly Subjective Tasks (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing evaluations of Large Language Models (LLMs) rely on a single large model to score outputs from other LLMs, but this is prone to intra-model bias and many tasks may be too subjective for a one model to judge fairly. |
| Approach: | They propose a language model council where a group of LLMs collaborate to create tests, respond to them, and evaluate each other’s responses to produce a ranking in a democratic fashion. |
| Outcome: | The proposed model produces rankings that are more separable and robust than any individual LLM judge. |
Improve LLM-as-a-Judge Ability as a General Ability (2025.emnlp-main)
Copied to clipboard
| Challenge: | Recent studies focus on generative judges, but only on their judge ability. |
| Approach: | They propose a method that leverages the generative and reasoning capabilities of large language models to evaluate LLM responses across diverse scenarios, providing accurate preference signals. |
| Outcome: | The proposed model performs on RewardBench with only 2% to 40% of the data required by other training frameworks. |
Improving Reward Models with Synthetic Critiques (2025.findings-naacl)
Copied to clipboard
| Challenge: | a recent study shows that reward models overfit on superficial features, hindering generalization performance . prevailing approach to training preference-based reward models presents several challenges . |
| Approach: | They propose a method that uses synthetic natural language critiques to provide additional feedback to large language models. |
| Outcome: | The proposed approach improves performance and data efficiency of RMs initialized from different pretrained models, reducing the reliance on costly human annotations. |