activity
20152026
most citeddeltaBLEU: A Discriminative Metric for Generation Tasks with Intrinsically Diverse Targets

95 citations · 417 across the 43 of their papers we have counts for

collaborators
Showing 2024Show all

7 papers · 1 filter

cs.LG2024★ 2 cited

Not All LLM Reasoners Are Created Equal

Arian Hosseini, Alessandro Sordoni, Daniel Toyama +2

We study the depth of grade-school math (GSM) problem-solving capabilities of LLMs. To this end, we evaluate their performance on pairs of existing math word problems together so t…

cs.LG2024★ 1 cited

VinePPO: Refining Credit Assignment in RL Training of LLMs

Amirhossein Kazemnejad, Milad Aghajohari, Eva Portelance +4

Large language models (LLMs) are increasingly applied to complex reasoning tasks that require executing several complex steps before receiving any reward. Properly assigning credit…

cs.LG2024

A Survey on Model MoErging: Recycling and Routing Among Specialized Experts for Collaborative Learning

Prateek Yadav, Colin Raffel, Mohammed Muqeeth +6

The availability of performant pre-trained models has led to a proliferation of fine-tuned expert models that are specialized to a particular domain or task. Model MoErging methods…

cs.CL2024★ 1 cited

Improving Context-Aware Preference Modeling for Language Models

Silviu Pitis, Ziang Xiao, Nicolas Le Roux +1

While finetuning language models from pairwise preferences has proven remarkably effective, the underspecified nature of natural language presents critical challenges. Direct prefe…

cs.LG2024

Towards Modular LLMs by Building and Reusing a Library of LoRAs

Oleksiy Ostapenko, Zhan Su, Edoardo Maria Ponti +5

The growing number of parameter-efficient adaptations of a base large language model (LLM) calls for studying whether we can reuse such trained adapters to improve performance for…

cs.LG2024★ 3 cited

Efficient Adversarial Training in LLMs with Continuous Attacks

Sophie Xhonneux, Alessandro Sordoni, Stephan Günnemann +2

Large language models (LLMs) are vulnerable to adversarial attacks that can bypass their safety guardrails. In many domains, adversarial training has proven to be one of the most p…