6 papers
Inference-Time Code Selection via Symbolic Equivalence Partitioning
David Cho, Yifan Wang, Fanping Sui +1
Sampling multiple candidate programs at inference time is an effective way to improve LLM code generation. However, its benefit depends on reliably selecting a correct solution fro…
SARL: Label-Free Reinforcement Learning by Rewarding Reasoning Topology
Yifan Wang, Bolian Li, David Cho +3
Reinforcement learning is critical to improving large reasoning models, but its success relies heavily on verifiable rewards (RLVR), making it hard to use in open-ended domains whe…
LLMs Can Get "Brain Rot": A Pilot Study on Twitter/X
Shuo Xing, Junyuan Hong, Yifan Wang +5
We propose and test the LLM Brain Rot Hypothesis: continual exposure to junk web text induces lasting cognitive decline in large language models (LLMs). To unveil junk effects, we…
DRIFT: Learning from Abundant User Dissatisfaction in Real-World Preference Learning
Yifan Wang, Bolian Li, Junlin Wu +5
Real-world large language model deployments (e.g., conversational AI systems, code generation assistants) naturally generate abundant implicit user dissatisfaction (DSAT) signals,…
Cascade Reward Sampling for Efficient Decoding-Time Alignment
Bolian Li, Yifan Wang, Anamika Lochab +2
Aligning large language models (LLMs) with human preferences is essential for their applications. Recently, decoding-time alignment has emerged as an effective plug-and-play techni…
More is Less: The Pitfalls of Multi-Model Synthetic Preference Data in DPO Safety Alignment
Yifan Wang, Runjin Chen, Bolian Li +7
Aligning large language models (LLMs) with human values is an increasingly critical step in post-training. Direct Preference Optimization (DPO) has emerged as a simple, yet effecti…