2 citations · 5 across the 16 of their papers we have counts for
9 papers · 1 filter
Learning Agent Routing From Early Experience
Yimin Wang, Jiahao Qiu, Xuan Qi +6
LLM agents achieve strong performance on complex reasoning tasks but incur high latency and compute cost. In practice, many queries fall within the capability boundary of cutting-e…
On the Role of Preference Variance in Preference Optimization
Jiacheng Guo, Zihao Li, Jiahao Qiu +2
Direct Preference Optimization (DPO) has emerged as an important approach for learning from human preferences in aligning large language models (LLMs). However, collecting human pr…
Shallow Preference Signals: Large Language Model Aligns Even Better with Truncated Data?
Xuan Qi, Jiahao Qiu, Xinzhe Juan +2
Aligning large language models (LLMs) with human preferences remains a key challenge in AI. Preference-based optimization methods, such as Reinforcement Learning with Human Feedbac…
Collab: Controlled Decoding using Mixture of Agents for LLM Alignment
Souradip Chakraborty, Sujay Bhatt, Udari Madhushani Sehwag +7
Alignment of Large Language models (LLMs) is crucial for safe and trustworthy deployment in applications. Reinforcement learning from human feedback (RLHF) has emerged as an effect…
Temporal Consistency for LLM Reasoning Process Error Identification
Jiacheng Guo, Yue Wu, Jiahao Qiu +4
Verification is crucial for effective mathematical reasoning. We present a new temporal consistency method where verifiers iteratively refine their judgments based on the previous…
Fast Best-of-N Decoding via Speculative Rejection
Hanshi Sun, Momin Haider, Ruiqi Zhang +6
The safe and effective deployment of Large Language Models (LLMs) involves a critical step called alignment, which ensures that the model's responses are in accordance with human p…
TreeBoN: Enhancing Inference-Time Alignment with Speculative Tree-Search and Best-of-N Sampling
Jiahao Qiu, Yifu Lu, Yifan Zeng +9
Inference-time alignment enhances the performance of large language models without requiring additional training or fine-tuning but presents challenges due to balancing computation…
PERSONA: A Reproducible Testbed for Pluralistic Alignment
Louis Castricato, Nathan Lile, Rafael Rafailov +2
The rapid advancement of language models (LMs) necessitates robust alignment with diverse user values. However, current preference optimization approaches often fail to capture the…
MaxMin-RLHF: Alignment with Diverse Human Preferences
Souradip Chakraborty, Jiahao Qiu, Hui Yuan +5
Reinforcement Learning from Human Feedback (RLHF) aligns language models to human preferences by employing a singular reward model derived from preference data. However, such an ap…