AIConfPaper
← Search

Victor Dibia

4 accepted papers

2025

Concept Distillation from Strong to Weak Models via Hypotheses-to-Theories Prompting

Emmanuel Aboah Boateng, Cassiano O Becker, Nabiha Asghar, Kabir Walia, Ashwin Srinivasan, Ehi Nosakhare +2
NAACL 2025industry

Hand-crafting high quality prompts to optimize the performance of language models is a complicated and labor-intensive process. Furthermore, when migrating to newer, smaller, or weaker models (possibly due to latency or cost gains), prompts need to be updated to re-optimize the task performance. We…

Cited by 0Source ↗PDF ↗Scholar ↗
2024

AUTOGEN STUDIO: A No-Code Developer Tool for Building and Debugging Multi-Agent Systems

Victor Dibia, Jingya Chen, Gagan Bansal, Suff Syed, Adam Fourney, Erkang Zhu +2
EMNLP 2024system demonstrations

Multi-agent systems, where multiple agents (generative AI models + tools) collaborate, are emerging as an effective pattern for solving long-running, complex tasks in numerous do- mains. However, specifying their parameters (such as models, tools, and orchestration mechanisms etc,.) and debugging th…

Cited by 4Source ↗PDF ↗code ↗Scholar ↗
2023

Aligning Offline Metrics and Human Judgments of Value for Code Generation Models

Victor Dibia, Adam Fourney, Gagan Bansal, Forough Poursabzi-Sangdeh, Han Liu, Saleema Amershi
ACL 2023findings

Large language models have demonstrated great potential to assist programmers in generating code. For such human-AI pair programming scenarios, we empirically demonstrate that while generated code are most often evaluated in terms of their functional correctness (i.e., whether generations pass avail…

Cited by 11Source ↗PDF ↗Scholar ↗
2023

Axiomatic Preference Modeling for Longform Question Answering

Corby Rosset, Guoqing Zheng, Victor Dibia, Ahmed Hassan Awadallah, Paul N. Bennett
EMNLP 2023long main

The remarkable abilities of large language models (LLMs) like ChatGPT and GPT-4 partially stem from the post-training processes involving human preferences encoded within a reward model as part of a Reinforcement Learning from Human Feedback (RLHF) regimen. These reward models (RMs) often lack dire…

Cited by 0Source ↗Scholar ↗