PERM: Psychology-grounded Empathetic Reward Modeling for Large Language Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing reward models evaluate empathy from a single perspective, overlooking bidirectional interaction nature of empathy. |
| Approach: | They propose a reward model that evaluates empathy from a single perspective . they propose PERM to integrate a bystander perspective to monitor overall interaction quality . |
| Outcome: | a new reward model outperforms state-of-the-art models on an emotional intelligence benchmark and an industrial daily conversation dataset. |
Similar Papers
Harnessing the Power of Large Language Models for Empathetic Response Generation: Empirical Investigations and Improvements (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Empathetic dialogue is an essential part of building harmonious social relationships and contributes to the development of a helpful AI. |
| Approach: | They propose three methods to improve the performance of large language models (LLMs) they propose semantically similar in-context learning, two-stage interactive generation and combination with the knowledge base. |
| Outcome: | The proposed methods achieve state-of-the-art in automatic and human evaluations and the possibility of GPT-4 simulating human evaluators. |
A Comprehensive Survey on Learning from Rewards for Large Language Models: Reward Models and Learning Strategies (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Recent developments in Large Language Models have shifted from pre-training to post-training and test-time scaling. |
| Approach: | They present a comprehensive overview of learning from rewards from the perspective of reward models and learning strategies across training, inference, and post-inference stages. |
| Outcome: | The proposed paradigm enables the transition from passive learning from static data to active learning from dynamic feedback. |
Tailored Emotional LLM-Supporter: Enhancing Cultural Sensitivity (2026.eacl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) have shown growing potential in offering emotional support, but their ability to deliver culturally sensitive support remains underexplored due to a lack of resources. |
| Approach: | They propose a large language model dataset that includes 1,729 distress messages, 1,523 cultural signals and 1,041 support strategies with fine-grained emotional and cultural annotations. |
| Outcome: | The proposed models outperform peer-reviewed models and lack cultural sensitivity. |
Can Machines Resonate with Humans? Evaluating the Emotional and Empathic Comprehension of LMs (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Empathy plays a pivotal role in fostering prosocial behavior, often triggered by the sharing of personal experiences through narratives. |
| Approach: | They propose to use contrastive learning with masked LMs and supervised fine-tuning with large language models to improve empathy understanding in NLP models. |
| Outcome: | The proposed methods show that there is low agreement among annotators and that cultural differences are a factor in their interpretation of empathy. |
The Pursuit of Empathy: Evaluating Small Language Models for PTSD Dialogue Support (2025.emnlp-main)
Copied to clipboard
Suhas Bn, Yash Mahajan, Dominik O. Mattioli, Andrew M. Sherrill, Rosa I. Arriaga, Christopher Wiese, Saeed Abdullah
| Challenge: | Claude Sonnet 3.5 consistently outperforms all models, but smaller models often approach human-rated empathy levels. |
| Approach: | They introduce a dataset comprising 10,000 two-turn conversations across 500 diverse, clinically-grounded PTSD personas. |
| Outcome: | The proposed model outperforms all models but has a "knowledge transfer ceiling" older adults prefer validation responses while graduate-educated users prefer emotionally layered responses . |
A Comprehensive Survey of Process Reward Models: Data Generation, Model Construction, and Usage (2026.acl-long)
Copied to clipboard
Congmin Zheng, Jiachen Zhu, Zhuoying Ou, Yuxiang Chen, Kangning Zhang, Rong Shan, Zeyu Zheng, Mengyue Yang, Jianghao Lin, Yong Yu, Weinan Zhang
| Challenge: | Large Language Models (LLMs) have advanced reasoning ability, yet conventional alignment remains dominated by outcome reward models that judge only final answers. |
| Approach: | They summarize applications across math, code, text, multimodal reasoning, robotics, and agents . goal is to clarify design spaces, reveal open challenges, and guide future research toward fine-grained, robust reasoning alignment. |
| Outcome: | The proposed model enables finer credit assignment, richer diagnostics, and improved robustness. |
Empathetic Persuasion: Reinforcing Empathy and Persuasiveness in Dialogue Systems (2022.findings-naacl)
Copied to clipboard
| Challenge: | Existing models for persuasive dialogue lack emotion annotated data, so we use transformers to provide emotion based feedbacks to our RL agent. |
| Approach: | They propose to use a language model to generate empathetic persuasive dialogues . they annotate existing data with emotions and build transformers to provide feedbacks based on emotion. |
| Outcome: | The proposed model increases the rate of generating persuasive responses compared to state-of-the-art models while maintaining the language quality. |
R-PRM: Reasoning-Driven Process Reward Modeling (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing Process Reward Models (PRMs) output evaluation scores directly, limiting both learning efficiency and evaluation accuracy. |
| Approach: | They propose a Reasoning-Driven Process Reward Modeling (R-PRM) which activates inherent reasoning to enhance process-level evaluation. |
| Outcome: | The proposed model outperforms baseline models on ProcessBench and PRMBench by 13.9 and 8.5 F1 scores. |
MotiveBench: How Far Are We From Human-Like Motivational Reasoning in Large Language Models? (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing benchmarks for large language models lack information asymmetry with real-world situations. |
| Approach: | They propose a benchmark to evaluate the human-like motivational and behavioral reasoning ability of LLMs with detailed, realistic situations. |
| Outcome: | The proposed benchmark compared LLMs with real-world scenarios on seven model families and found that the most advanced models struggle with understanding "love & belonging" needs. |
ReflectRM: Boosting Generative Reward Models via Self-Reflection within a Unified Judgment Framework (2026.acl-long)
Copied to clipboard
Kai Qin, Liangxin Liu, Yu Liang, Longzheng Wang, null Wangyan, Zhang Yueyang, Long Xia, Zhiyuan Sun, Houde Liu, Daiting Shi
| Challenge: | Existing methods for generating reward models focus on outcome-level supervision, neglecting analytical process quality, which constrains their potential. |
| Approach: | They propose a novel reward model that leverages self-reflection to assess analytical quality and enhance preference modeling. |
| Outcome: | The proposed model improves performance on four benchmarks and significantly mitigates positional bias. |