ContraCLM: Contrastive Learning For Causal Language Model
Nihal Jain, Dejiao Zhang, Wasi Uddin Ahmad, Zijian Wang, Feng Nan, Xiaopeng Li, Ming Tan, Ramesh Nallapati, Baishakhi Ray, Parminder Bhatia, Xiaofei Ma, Bing Xiang
Anthology
Underline
Main: Machine Learning for NLP Main-poster Paper
Poster Session 6: Machine Learning for NLP (Poster)
Conference Room: Frontenac Ballroom and Queen's Quay
Conference Time: July 12, 09:00-10:30 (EDT) (America/Toronto)
Global Time: July 12, Poster Session 6 (13:00-14:30 UTC)
Keywords:
contrastive learning
TLDR:
Despite exciting progress in causal language models, the expressiveness of their representations is largely limited due to poor discrimination ability. To remedy this issue, we present CONTRACLM, a novel contrastive learning framework at both the token-level and the sequence-level. We assess CONTRAC...
You can open the
#paper-P4482
channel in a separate window.
Abstract:
Despite exciting progress in causal language models, the expressiveness of their representations is largely limited due to poor discrimination ability. To remedy this issue, we present CONTRACLM, a novel contrastive learning framework at both the token-level and the sequence-level. We assess CONTRACLM on a variety of downstream tasks. We show that CONTRACLM enhances the discrimination of representations and bridges the gap with encoder-only models, which makes causal language models better suited for tasks beyond language generation. Specifically, we attain 44\% relative improvement on the Semantic Textual Similarity tasks and 34\% on Code-to-Code Search tasks. Furthermore, by improving the expressiveness of representations, CONTRACLM also boosts the source code generation capability with 9\% relative improvement on execution accuracy on the HumanEval benchmark.