Papers with finetune language models

3 papers
Few-Shot Data Synthesis for Open Domain Multi-Hop Question Answering (2024.eacl-long)

Copied to clipboard

Challenge: Recent approaches to multi-hop question answering rely on in-context learning . however, these models contain billions of parameters making them inefficient at inference time.
Approach: They propose a framework that allows for improving smaller language models with less than 10 human-annotated QA pairs by synthesizing millions of multi-hop questions and claims to fine tune language models.
Outcome: The proposed framework improves model performance on multi-hop question answering and fact verification benchmarks while being almost one-third the size in parameter count.
Context-Aware Language Modeling for Goal-Oriented Dialogue Systems (2022.findings-naacl)

Copied to clipboard

Challenge: Goal-oriented dialogue systems face a trade-off between fluent language generation and task-specific control.
Approach: They propose a method to fine-tune language models in a goal-aware way . they evaluate a flight-booking method with a context-assisted language model .
Outcome: The proposed method outperforms the state-of-the-art method on a flight-booking task by 7% in terms of task success.
Loose lips sink ships: Mitigating Length Bias in Reinforcement Learning from Human Feedback (2023.findings-emnlp)

Copied to clipboard

Challenge: Experimental results prove that language models can learn from human feedback better, irrespective of sequence length . emergence of length bias often induces the model to favor longer outputs .
Approach: They propose to separate reward modeling from the influence of sequence length by using the Product-of-Experts technique.
Outcome: The proposed approach shows that language models perform better regardless of sequence length . the main expert is focused on understanding human intents, while the biased expert targets the identification and capture of length bias.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations