Get our free extension to see links to code for papers anywhere online!

Add to Chrome

Add to Firefox

Picture for Chenhao Tan

Chenhao Tan

Probing Classifiers are Unreliable for Concept Removal and Detection

Jul 08, 2022
Abhinav Kumar, Chenhao Tan, Amit Sharma

Figure 1 for Probing Classifiers are Unreliable for Concept Removal and Detection

Figure 2 for Probing Classifiers are Unreliable for Concept Removal and Detection

Figure 3 for Probing Classifiers are Unreliable for Concept Removal and Detection

Figure 4 for Probing Classifiers are Unreliable for Concept Removal and Detection

Access Paper or Ask Questions

Learning to Ignore Adversarial Attacks

May 23, 2022
Yiming Zhang, Yangqiaoyu Zhou, Samuel Carton, Chenhao Tan

Figure 1 for Learning to Ignore Adversarial Attacks

Figure 2 for Learning to Ignore Adversarial Attacks

Figure 3 for Learning to Ignore Adversarial Attacks

Figure 4 for Learning to Ignore Adversarial Attacks

* 14 pages, 2 figures

Access Paper or Ask Questions

Human-AI Collaboration via Conditional Delegation: A Case Study of Content Moderation

Apr 25, 2022
Vivian Lai, Samuel Carton, Rajat Bhatnagar, Q. Vera Liao, Yunfeng Zhang, Chenhao Tan

Figure 1 for Human-AI Collaboration via Conditional Delegation: A Case Study of Content Moderation

Figure 2 for Human-AI Collaboration via Conditional Delegation: A Case Study of Content Moderation

Figure 3 for Human-AI Collaboration via Conditional Delegation: A Case Study of Content Moderation

Figure 4 for Human-AI Collaboration via Conditional Delegation: A Case Study of Content Moderation

* 18 pages, 44 figures

Access Paper or Ask Questions

Machine Explanations and Human Understanding

Feb 08, 2022
Chacha Chen, Shi Feng, Amit Sharma, Chenhao Tan

* 26 pages, 13 figures

Access Paper or Ask Questions

Rethinking Explainability as a Dialogue: A Practitioner's Perspective

Feb 03, 2022
Himabindu Lakkaraju, Dylan Slack, Yuxin Chen, Chenhao Tan, Sameer Singh

Figure 1 for Rethinking Explainability as a Dialogue: A Practitioner's Perspective

Access Paper or Ask Questions

Towards a Science of Human-AI Decision Making: A Survey of Empirical Studies

Dec 21, 2021
Vivian Lai, Chacha Chen, Q. Vera Liao, Alison Smith-Renner, Chenhao Tan

Figure 1 for Towards a Science of Human-AI Decision Making: A Survey of Empirical Studies

Figure 2 for Towards a Science of Human-AI Decision Making: A Survey of Empirical Studies

Figure 3 for Towards a Science of Human-AI Decision Making: A Survey of Empirical Studies

Figure 4 for Towards a Science of Human-AI Decision Making: A Survey of Empirical Studies

* 36 pages, 2 figures, see https://haidecisionmaking.github.io for website

Access Paper or Ask Questions

What to Learn, and How: Toward Effective Learning from Rationales

Nov 30, 2021
Samuel Carton, Surya Kanoria, Chenhao Tan

Figure 1 for What to Learn, and How: Toward Effective Learning from Rationales

Figure 2 for What to Learn, and How: Toward Effective Learning from Rationales

Figure 3 for What to Learn, and How: Toward Effective Learning from Rationales

Figure 4 for What to Learn, and How: Toward Effective Learning from Rationales

* 13 pages, 8 figures

Access Paper or Ask Questions

Investigating the Effect of Natural Language Explanations on Out-of-Distribution Generalization in Few-shot NLI

Oct 12, 2021
Yangqiaoyu Zhou, Chenhao Tan

Figure 1 for Investigating the Effect of Natural Language Explanations on Out-of-Distribution Generalization in Few-shot NLI

Figure 2 for Investigating the Effect of Natural Language Explanations on Out-of-Distribution Generalization in Few-shot NLI

Figure 3 for Investigating the Effect of Natural Language Explanations on Out-of-Distribution Generalization in Few-shot NLI

Figure 4 for Investigating the Effect of Natural Language Explanations on Out-of-Distribution Generalization in Few-shot NLI

* 8 pages, 4 figures, EMNLPWorkshop on Insights from Negative Results in NLP 2021, data is available at https://github.com/ChicagoHAI/hans-explanations

Access Paper or Ask Questions

Decision-Focused Summarization

Sep 14, 2021
Chao-Chun Hsu, Chenhao Tan

Figure 1 for Decision-Focused Summarization

Figure 2 for Decision-Focused Summarization

Figure 3 for Decision-Focused Summarization

Figure 4 for Decision-Focused Summarization

* 16 pages, 10 figures, EMNLP 2021, code is available at https://github.com/ChicagoHAI/decsum

Access Paper or Ask Questions

On Positivity Bias in Negative Reviews

Jun 22, 2021
Madhusudhan Aithal, Chenhao Tan

Figure 1 for On Positivity Bias in Negative Reviews

Figure 2 for On Positivity Bias in Negative Reviews

Figure 3 for On Positivity Bias in Negative Reviews

Figure 4 for On Positivity Bias in Negative Reviews

* 11 pages, 17 figures, ACL 2021

Access Paper or Ask Questions