Alert button
Picture for Yftah Ziser

Yftah Ziser

Alert button

Spectral Editing of Activations for Large Language Model Alignment

Add code
Bookmark button
Alert button
May 15, 2024
Yifu Qiu, Zheng Zhao, Yftah Ziser, Anna Korhonen, Edoardo M. Ponti, Shay B. Cohen

Figure 1 for Spectral Editing of Activations for Large Language Model Alignment
Figure 2 for Spectral Editing of Activations for Large Language Model Alignment
Figure 3 for Spectral Editing of Activations for Large Language Model Alignment
Figure 4 for Spectral Editing of Activations for Large Language Model Alignment
Viaarxiv icon

Are Large Language Models Temporally Grounded?

Add code
Bookmark button
Alert button
Nov 16, 2023
Yifu Qiu, Zheng Zhao, Yftah Ziser, Anna Korhonen, Edoardo M. Ponti, Shay B. Cohen

Viaarxiv icon

A Joint Matrix Factorization Analysis of Multilingual Representations

Add code
Bookmark button
Alert button
Oct 24, 2023
Zheng Zhao, Yftah Ziser, Bonnie Webber, Shay B. Cohen

Viaarxiv icon

Detecting and Mitigating Hallucinations in Multilingual Summarisation

Add code
Bookmark button
Alert button
May 23, 2023
Yifu Qiu, Yftah Ziser, Anna Korhonen, Edoardo M. Ponti, Shay B. Cohen

Figure 1 for Detecting and Mitigating Hallucinations in Multilingual Summarisation
Figure 2 for Detecting and Mitigating Hallucinations in Multilingual Summarisation
Figure 3 for Detecting and Mitigating Hallucinations in Multilingual Summarisation
Figure 4 for Detecting and Mitigating Hallucinations in Multilingual Summarisation
Viaarxiv icon

BERT is not The Count: Learning to Match Mathematical Statements with Proofs

Add code
Bookmark button
Alert button
Feb 18, 2023
Weixian Waylon Li, Yftah Ziser, Maximin Coavoux, Shay B. Cohen

Figure 1 for BERT is not The Count: Learning to Match Mathematical Statements with Proofs
Figure 2 for BERT is not The Count: Learning to Match Mathematical Statements with Proofs
Figure 3 for BERT is not The Count: Learning to Match Mathematical Statements with Proofs
Figure 4 for BERT is not The Count: Learning to Match Mathematical Statements with Proofs
Viaarxiv icon

Erasure of Unaligned Attributes from Neural Representations

Add code
Bookmark button
Alert button
Feb 06, 2023
Shun Shao, Yftah Ziser, Shay Cohen

Figure 1 for Erasure of Unaligned Attributes from Neural Representations
Figure 2 for Erasure of Unaligned Attributes from Neural Representations
Figure 3 for Erasure of Unaligned Attributes from Neural Representations
Figure 4 for Erasure of Unaligned Attributes from Neural Representations
Viaarxiv icon

Understanding Domain Learning in Language Models Through Subpopulation Analysis

Add code
Bookmark button
Alert button
Oct 22, 2022
Zheng Zhao, Yftah Ziser, Shay B. Cohen

Figure 1 for Understanding Domain Learning in Language Models Through Subpopulation Analysis
Figure 2 for Understanding Domain Learning in Language Models Through Subpopulation Analysis
Figure 3 for Understanding Domain Learning in Language Models Through Subpopulation Analysis
Figure 4 for Understanding Domain Learning in Language Models Through Subpopulation Analysis
Viaarxiv icon

Domain Adaptation from Scratch

Add code
Bookmark button
Alert button
Sep 02, 2022
Eyal Ben-David, Yftah Ziser, Roi Reichart

Figure 1 for Domain Adaptation from Scratch
Figure 2 for Domain Adaptation from Scratch
Figure 3 for Domain Adaptation from Scratch
Figure 4 for Domain Adaptation from Scratch
Viaarxiv icon

Factorizing Content and Budget Decisions in Abstractive Summarization of Long Documents by Sampling Summary Views

Add code
Bookmark button
Alert button
May 25, 2022
Marcio Fonseca, Yftah Ziser, Shay B. Cohen

Figure 1 for Factorizing Content and Budget Decisions in Abstractive Summarization of Long Documents by Sampling Summary Views
Figure 2 for Factorizing Content and Budget Decisions in Abstractive Summarization of Long Documents by Sampling Summary Views
Figure 3 for Factorizing Content and Budget Decisions in Abstractive Summarization of Long Documents by Sampling Summary Views
Figure 4 for Factorizing Content and Budget Decisions in Abstractive Summarization of Long Documents by Sampling Summary Views
Viaarxiv icon

Gold Doesn't Always Glitter: Spectral Removal of Linear and Nonlinear Guarded Attribute Information

Add code
Bookmark button
Alert button
Mar 15, 2022
Shun Shao, Yftah Ziser, Shay B. Cohen

Figure 1 for Gold Doesn't Always Glitter: Spectral Removal of Linear and Nonlinear Guarded Attribute Information
Figure 2 for Gold Doesn't Always Glitter: Spectral Removal of Linear and Nonlinear Guarded Attribute Information
Figure 3 for Gold Doesn't Always Glitter: Spectral Removal of Linear and Nonlinear Guarded Attribute Information
Figure 4 for Gold Doesn't Always Glitter: Spectral Removal of Linear and Nonlinear Guarded Attribute Information
Viaarxiv icon