- Elo-Evolve: A Co-evolutionary Framework for Language Model Alignment
Jing Zhao, Ting Zhen, Junwei Bao, Hongfei Jiang, Yang Song · Feb 14, 2026 · Citations: 0
Pairwise Preference Automatic Metrics
Current alignment methods for Large Language Models (LLMs) rely on compressing vast amounts of human preference data into static, absolute reward functions, leading to data scarcity, noise sensitivity, and training instability.
- DSPA: Dynamic SAE Steering for Data-Efficient Preference Alignment
James Wedgwood, Aashiq Muhamed, Mona T. Diab, Virginia Smith · Mar 23, 2026 · Citations: 0
Pairwise Preference Automatic Metrics
Preference alignment is usually achieved by weight-updating training on preference data, which adds substantial alignment-stage compute and provides limited mechanistic visibility.
- GIFT: Group-Relative Implicit Fine-Tuning Integrates GRPO with DPO and UNA
Zhichao Wang · Oct 27, 2025 · Citations: 0
Pairwise Preference Automatic Metrics
This paper proposes Group-relative Implicit Fine-Tuning (GIFT), a reinforcement learning framework for aligning large language models (LLMs) that unifies on-policy optimization with implicit preference learning.
- Top-b: Entropic Regulation of Relative Probability Bands in Autoregressive Language Processes
Deepon Halder, Raj Dabre · Mar 15, 2026 · Citations: 0
Automatic Metrics
Empirical validation on GPQA and GSM8K benchmarks indicates that Top-b significantly reduces generation entropy and inter-decoding variance while maintaining competitive reasoning accuracy, effectively approximating a self-regulating…
- D-COT: Disciplined Chain-of-Thought Learning for Efficient Reasoning in Small Language Models
Shunsuke Ubukata · Feb 25, 2026 · Citations: 0
Automatic Metrics
In this study, we propose Disciplined Chain-of-Thought (D-CoT), a novel framework that enforces a structured reasoning process using control tags -- such as <TEMP_LOW> for fact-checking and <TEMP_HIGH> for multi-perspective exploration --…
- PIKA: Expert-Level Synthetic Datasets for Post-Training Alignment from Scratch
Shangjian Yin, Shining Liang, Wenbiao Ding, Yuli Qian, Zhouxing Shi · Oct 8, 2025 · Citations: 0
Pairwise Preference
Despite its small size, fine-tuning Llama-3-8B-Base on PiKa-SFT even outperforms the official Llama-3-8B-Instruct model trained on over 10M proprietary examples on widely used benchmarks such as AlpacaEval 2.0 and Arena-Hard.
- Revisiting Self-Play Preference Optimization: On the Role of Prompt Difficulty
Yao Xiao, Jung-jae Kim, Roy Ka-wei Lee, Lidong Bing · Oct 7, 2025 · Citations: 0
Pairwise Preference
Self-play preference optimization has emerged as a prominent paradigm for aligning large language models (LLMs).
- DeepPrune: Parallel Scaling without Inter-trace Redundancy
Shangqing Tu, Yaxuan Li, Yushi Bai, Lei Hou, Juanzi Li · Oct 9, 2025 · Citations: 0
Llm As JudgeAutomatic Metrics
Our method features a specialized judge model trained with out-of-distribution data (AIME 2022, AIME 2023, and MATH 500) using oversampling techniques to accurately predict answer equivalence from partial reasoning traces, achieving 0.7072…
- TARo: Token-level Adaptive Routing for LLM Test-time Alignment
Arushi Rai, Qiang Zhang, Hanqing Zeng, Yunkai Zhang, Dipesh Tamboli · Mar 19, 2026 · Citations: 0
Pairwise Preference
Recent test-time alignment methods offer a lightweight alternative, but have been explored mainly for preference alignment rather than reasoning.
- Schema for In-Context Learning
Pan Chen, Shaohong Chen, Mark Wang, Shi Xuan Leong, Priscilla Fung · Oct 14, 2025 · Citations: 0
Demonstrations
Inspired by cognitive science, specifically schema theory, which holds that humans interpret new information by activating pre-existing mental frameworks (schemas) to structure understanding, we introduce Schema-Activated In-Context…
- Alignment through Meta-Weighted Online Sampling: Bridging the Gap between Data Generation and Preference Optimization
Junming Yang, Ning Xu, Biao Liu, Shiqi Qiao, Xin Geng · Sep 27, 2025 · Citations: 0
Pairwise Preference
To bridge this gap, we propose Meta-Weighted Adaptive Preference Optimization (MetaAPO), a novel framework that dynamically couples data generation with model training.
- Towards Bridging the Reward-Generation Gap in Direct Alignment Algorithms
Zeguan Xiao, Yun Chen, Guanhua Chen, Ke Tang · Jun 11, 2025 · Citations: 0
Pairwise Preference
Direct Alignment Algorithms (DAAs), such as Direct Preference Optimization (DPO) and Simple Preference Optimization (SimPO), have emerged as efficient alternatives to Reinforcement Learning from Human Feedback (RLHF) algorithms for aligning…
- C2: Scalable Rubric-Augmented Reward Modeling from Binary Preferences
Akira Kawabata, Saku Sugawara · Apr 15, 2026 · Citations: 0
- Activation Steering for Aligned Open-ended Generation without Sacrificing Coherence
Niklas Herbster, Martin Zborowski, Alberto Tosato, Gauthier Gidel, Tommaso Tosato · Apr 9, 2026 · Citations: 0
- Sensitivity-Positional Co-Localization in GQA Transformers
Manoj Chandrashekar Rao · Apr 9, 2026 · Citations: 0
- Squeeze Evolve: Unified Multi-Model Orchestration for Verifier-Free Evolution
Monishwaran Maheswaran, Leon Lakhani, Zhongzhu Zhou, Shijia Yang, Junxiong Wang · Apr 9, 2026 · Citations: 0
- Off-Policy Value-Based Reinforcement Learning for Large Language Models
Peng-Yuan Wang, Ziniu Li, Tian Xu, Bohan Yang, Tian-Shuo Liu · Mar 24, 2026 · Citations: 0
- Lie to Me: How Faithful Is Chain-of-Thought Reasoning in Reasoning Models?
Richard J. Young · Mar 23, 2026 · Citations: 0
- Mediocrity is the key for LLM as a Judge Anchor Selection
Shachar Don-Yehiya, Asaf Yehudai, Leshem Choshen, Omri Abend · Mar 17, 2026 · Citations: 0
- TERMINATOR: Learning Optimal Exit Points for Early Stopping in Chain-of-Thought Reasoning
Alliot Nagle, Jakhongir Saydaliev, Dhia Garbaya, Michael Gastpar, Ashok Vardhan Makkuva · Mar 13, 2026 · Citations: 0
- CHIMERA: Compact Synthetic Data for Generalizable LLM Reasoning
Xinyu Zhu, Yihao Feng, Yanchao Sun, Xianzhi Du, Pingzhi Li · Mar 1, 2026 · Citations: 0