1 citations · 2 across the 8 of their papers we have counts for
8 papers
Learning with a Single Rollout via Pass@k Policy Optimization
Fengdi Che, Yang Liu, Lei Yu +4
Group Relative Policy Optimization (GRPO) typically requires multiple rollouts per prompt to estimate relative credit, incurring substantial sampling cost and exacerbating training…
MapSatisfyBench: Benchmarking Satisfaction-Aware Map Agents through Behavior-Grounded Implicit Decision Factors
Lubin Bai, Mengyu Cao, Sixue Wang +5
Large language model agents are increasingly integrated into map services. Since map services are embedded in everyday-life scenarios rather than professional task settings, users…
Stochastic Chameleons: Irrelevant Context Hallucinations Reveal Class-Based (Mis)Generalization in LLMs
Ziling Cheng, Meng Cao, Marc-Antoine Rondeau +1
The widespread success of large language models (LLMs) on NLP benchmarks has been accompanied by concerns that LLMs function primarily as stochastic parrots that reproduce texts si…
Can LLMs Reason Abstractly Over Math Word Problems Without CoT? Disentangling Abstract Formulation From Arithmetic Computation
Ziling Cheng, Meng Cao, Leila Pishdad +2
Final-answer-based metrics are commonly used for evaluating large language models (LLMs) on math word problems, often taken as proxies for reasoning ability. However, such metrics…
The Reasoning-Memorization Interplay in Language Models Is Mediated by a Single Direction
Yihuai Hong, Dian Zhou, Meng Cao +2
Large language models (LLMs) excel on a variety of reasoning benchmarks, but previous studies suggest they sometimes struggle to generalize to unseen questions, potentially due to…
Mechanistic Understanding and Mitigation of Language Model Non-Factual Hallucinations
Lei Yu, Meng Cao, Jackie Chi Kit Cheung +1
State-of-the-art language models (LMs) sometimes generate non-factual hallucinations that misalign with world knowledge. To explore the mechanistic causes of these hallucinations,…
Responsible AI Considerations in Text Summarization Research: A Review of Current Practices
Yu Lu Liu, Meng Cao, Su Lin Blodgett +3
AI and NLP publication venues have increasingly encouraged researchers to reflect on possible ethical considerations, adverse impacts, and other responsible AI issues their work mi…
Successor Features for Efficient Multisubject Controlled Text Generation
Meng Cao, Mehdi Fatemi, Jackie Chi Kit Cheung +1
While large language models (LLMs) have achieved impressive performance in generating fluent and realistic text, controlling the generated text so that it exhibits properties such…