Papers by Ari Kobren

4 papers
Optimal Transport-based Alignment of Learned Character Representations for String Similarity (P19-1)

Copied to clipboard

Challenge: String similarity models are crucial for record linkage, data integration, search and entity resolution systems.
Approach: They propose a model that encodes the characters of each string, aligns the encodings using Sinkhorn Iteration and scores the alignment with a convolutional neural network.
Outcome: The proposed model outperforms state-of-the-art and classical similarity models on four of the five datasets and improves performance by applying it to cross-document coreference.
Upstream Mitigation Is Not All You Need: Testing the Bias Transfer Hypothesis in Pre-Trained Language Models (2022.acl-long)

Copied to clipboard

Challenge: Large language models and other massively pre-trained "foundation" models can easily adapt to a wide variety of downstream tasks in a process called finetuning.
Approach: They propose to use the bias transfer hypothesis to reduce social biases internalized by large language models during pre-training into harmful task-specific behavior after fine-tuning.
Outcome: The bias transfer hypothesis is the theory that social biases internalized by large language models during pre-training transfer into harmful task-specific behavior after fine-tuning.
Don’t Just Clean It, Proxy Clean It: Mitigating Bias by Proxy in Pre-Trained Models (2022.findings-emnlp)

Copied to clipboard

Challenge: Transformer-based pre-trained models can encode societal biases in their contextual representations and in downstream predictions when fine-tuned on task-specific data.
Approach: They propose an approach that selectively eliminates stereotypical associations at fine-tuning, so that the model doesn't learn to excessively rely on those signals.
Outcome: The proposed approach reduces biases from identity words and frequently co-occurring proxies by > 60% in toxicity classification, and also extends to multiple identities.
Adaptive Question Answering: Enhancing Language Model Proficiency for Addressing Knowledge Conflicts with Source Citations (2024.emnlp-main)

Copied to clipboard

Challenge: Existing work on citation generation has focused on unambiguous settings with single answers, failing to address the complexity of real-world scenarios.
Approach: They propose a task of QA with source citation in ambiguous settings where multiple valid answers exist, where multiple sources exist.
Outcome: The proposed framework generates multiple answers and cites their sources, allowing users to verify the factuality of each answer and make informed decisions.

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