7 papers
Planning Commitment of LLM under Partial Observability
Cassie Huang, Zhanwei Cao, Yeawon Lee +7
LLM-based planning agents commit to plans of different lengths before interacting with a partially observable environment. Some aggressively commit to a long plan based on assumpti…
Asymmetric Capacity Allocation in Self-Refinement Pipelines
Zhuoyi Yang, Ian G. Harris, Salar Hashemitaheri +7
Self-refinement, typically structured as generation, critique, and revision, is a widely adopted paradigm for improving LLM generation and serves as a core mechanism in many LLM ag…
Language Models as Higher-Order Planning Formalizers
Owen Jiang, Cassie Huang, Ashish Sabharwal +1
Recent work provides overwhelming evidence that LLMs, even those trained to scale their reasoning trace, quickly deteriorate at planning as problems become more complex. LLM-as-For…
Language Model as Planner and Formalizer under Constraints
Cassie Huang, Stuti Mohan, Ziyi Yang +2
LLMs have been widely used in planning, either as planners to generate action sequences end-to-end, or as formalizers to represent the planning domain and problem in a formal langu…
Unifying Inference-Time Planning Language Generation
Prabhu Prakash Kagitha, Bo Sun, Ishan Desai +5
A line of work in planning uses LLM not to generate a plan, but to generate a formal representation in some planning language, which can be input into a symbolic solver to determin…
On the Limit of Language Models as Planning Formalizers
Cassie Huang, Li Zhang
Large Language Models have been found to create plans that are neither executable nor verifiable in grounded environments. An emerging line of work demonstrates success in using th…
Adversarial Examples Generation for Reducing Implicit Gender Bias in Pre-trained Models
Wenqian Ye, Fei Xu, Yaojia Huang +2
Over the last few years, Contextualized Pre-trained Neural Language Models, such as BERT, GPT, have shown significant gains in various NLP tasks. To enhance the robustness of exist…