Abstain-R1: Calibrated Abstention and Post-Refusal Clarification via Verifiable RL (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing abstention methods produce generic refusals or encourage follow-up clarifications without verifying whether they identify the key missing information. |
| Approach: | They propose a clarification-aware RLVR reward that rewards correct answers on unanswerable queries while optimizing explicit abstention and semantically aligned post-refusal clarification on unannounced queries. |
| Outcome: | The proposed model improves abstention and clarification on unanswerable queries while maintaining strong performance on answerable queries. |
Similar Papers
Mitigating Lost in Multi-turn Conversation via Curriculum RL with Verifiable Accuracy and Abstention Rewards (2026.acl-long)
Copied to clipboard
Ming Li, Pei Chen, Zhenhao Zhang, Tao Yang, Xinyang Zhang, Han Li, Tianyu Cao, Ming Zeng, Zhuofeng Wu, Meng Jiang, Huasheng Li, Lihong Li, Bing Yin
| Challenge: | Large Language Models exhibit strong capabilities in single-turn instruction following but suffer from Lost-in-Conversation (LiC) when instructions are revealed progressively in multi-turn settings, models get "Lost in Conversation" |
| Approach: | They propose a framework that encourages models to generate correct answers and judge solvability in multi-turn conversations. |
| Outcome: | The proposed framework improves models' ability to balance problem-solving with abstention . it reduces premature answering behaviors that cause lost-in-conversation (LiC) |
Beyond Reasoning Gains: Mitigating General-Capability Forgetting in Large Reasoning Models (2026.findings-acl)
Copied to clipboard
Hoang Phan, Xianjun Yang, Yuanshun Yao, Jingyu Zhang, Shengjie Bi, Xiaocheng Tang, Madian Khabsa, Lijuan Liu, Deren Lei
| Challenge: | Reinforcement learning with verifiable rewards (RLVR) has delivered impressive gains in mathematical and multimodal reasoning . however, the recipe introduces a significant risk of capability regression, where models forget foundational skills after prolonged training without employing regularization strategies. |
| Approach: | They propose a replay strategy with dynamic objective reweighting for general knowledge preservation using short-horizon signals of convergence and instability. |
| Outcome: | The proposed method preserves general capabilities and improves reasoning . it can be applied to existing RLVR pipelines without training additional models or tuning . |
Crossing the Reward Bridge: Expanding Reinforcement Learning with Verifiable Rewards Across Diverse Domains (2026.acl-long)
Copied to clipboard
| Challenge: | Reinforcement learning with verifiable rewards (RLVR) has been effective on structured tasks, but its reliance on simple, rule-based verifiers creates a bottleneck. |
| Approach: | They propose a framework that uses a generative verifier to provide soft, probabilistic rewards. |
| Outcome: | The proposed framework outperforms existing models up to 10x their size and can be scalable and effective. |
DARL: Encouraging Diverse Answers for General Reasoning without Verifiers (2026.findings-acl)
Copied to clipboard
| Challenge: | Recent efforts such as RLPR have extended RLVR to general domains, enabling training on broader datasets and achieving improvements over RL PR. |
| Approach: | They propose a framework that encourages the generation of diverse answers within a controlled deviation range from the reference while preserving alignment with it. |
| Outcome: | Extensive experiments on 13 benchmarks show that DARL surpasses RLPR in both reasoning accuracy and output diversity. |
Answering the Wrong Question: Reasoning Trace Inversion for Abstention in LLMs (2026.acl-long)
Copied to clipboard
| Challenge: | Large Language Models have been shown to have worse abstention abilities than reasoning models . a new class of abstraction methods is developed to improve absttention performance . |
| Approach: | They propose a class of abstention methods that generate reasoning trace and reconstruct most likely query from it. |
| Outcome: | The proposed method beats baselines in 33 out of 36 settings. |
Balancing Classification and Calibration Performance in Decision-Making LLMs via Calibration Aware Reinforcement Learning (2026.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) are increasingly deployed in decision-making tasks where accuracy and reliable confidence estimates are essential. |
| Approach: | They propose a calibration-aware reinforcement learning formulation that directly adjusts decision-token probabilities. |
| Outcome: | The proposed model preserves RLVR’s accuracy level while mitigating overconfidence, reducing ECE scores up to 9 points. |
Good Reasoning Makes Good Demonstrations: Implicit Reasoning Quality Supervision via In-Context Reinforcement Learning (2026.findings-acl)
Copied to clipboard
| Challenge: | Reinforcement Learning with Verifiable Rewards (RLVR) improves reasoning in large language models but treats all correct solutions equally, potentially reinforcing flawed traces that arrive at correct answers by chance. |
| Approach: | They propose a method that reweights rewards by a factor approximately proportional to Evidence Gain and assigns higher weights to high-quality traces without requiring costly computation. |
| Outcome: | Experiments on mathematical reasoning benchmarks show that Reinforcement Learning with Verifiable Rewards (RLVR) improves reasoning in large language models but treats all correct solutions equally. |
R1-RE: Cross-Domain Relation Extraction with RLVR (2026.acl-long)
Copied to clipboard
| Challenge: | Relation extraction (RE) is a core task in natural language processing. |
| Approach: | They propose a supervised learning task for relation extraction (RE) based on annotation guidelines. |
| Outcome: | The proposed model achieves an average OOD accuracy of 70%, on par with leading proprietary models such as GPT-4o. |
Alleviating Hallucinations from Knowledge Misalignment in Large Language Models via Selective Abstention Learning (2025.acl-long)
Copied to clipboard
Lei Huang, Xiaocheng Feng, Weitao Ma, Yuchun Fan, Xiachong Feng, Yuxuan Gu, Yangfan Ye, Liang Zhao, Weihong Zhong, Baoxin Wang, Dayong Wu, Guoping Hu, Lingpeng Kong, Tong Xiao, Ting Liu, Bing Qin
| Challenge: | Large language models (LLMs) suffer from severe hallucination issues due to the knowledge misalignment between the pre-training stage and the supervised fine-tuning stage. |
| Approach: | They propose a training objective with an abstention mechanism that selectively rejects tokens that misalign with the desired knowledge distribution via a special [REJ] token. |
| Outcome: | The proposed model selectively rejects tokens that misalign with the desired knowledge distribution via a special [REJ] token. |
Table-R1: Inference-Time Scaling for Table Reasoning Tasks (2025.emnlp-main)
Copied to clipboard
| Challenge: | In this study, we explore inference-time scaling on table reasoning tasks. |
| Approach: | They propose a large-scale dataset of reasoning traces and a reinforcement learning with verifiable rewards approach to enable inference-time scaling on table reasoning tasks. |
| Outcome: | The proposed model matches or exceeds GPT-4.1 and DeepSeek-R1 models on diverse table reasoning tasks. |