Picture for Mark J. F. Gales

Mark J. F. Gales

Efficient Sample-Specific Encoder Perturbations

May 01, 2024
Viaarxiv icon

Can GPT-4 do L2 analytic assessment?

Add code
Apr 29, 2024
Figure 1 for Can GPT-4 do L2 analytic assessment?
Figure 2 for Can GPT-4 do L2 analytic assessment?
Figure 3 for Can GPT-4 do L2 analytic assessment?
Figure 4 for Can GPT-4 do L2 analytic assessment?
Viaarxiv icon

WaterJudge: Quality-Detection Trade-off when Watermarking Large Language Models

Mar 28, 2024
Figure 1 for WaterJudge: Quality-Detection Trade-off when Watermarking Large Language Models
Figure 2 for WaterJudge: Quality-Detection Trade-off when Watermarking Large Language Models
Figure 3 for WaterJudge: Quality-Detection Trade-off when Watermarking Large Language Models
Figure 4 for WaterJudge: Quality-Detection Trade-off when Watermarking Large Language Models
Viaarxiv icon

Teacher-Student Training for Debiasing: General Permutation Debiasing for Large Language Models

Mar 20, 2024
Figure 1 for Teacher-Student Training for Debiasing: General Permutation Debiasing for Large Language Models
Figure 2 for Teacher-Student Training for Debiasing: General Permutation Debiasing for Large Language Models
Figure 3 for Teacher-Student Training for Debiasing: General Permutation Debiasing for Large Language Models
Figure 4 for Teacher-Student Training for Debiasing: General Permutation Debiasing for Large Language Models
Viaarxiv icon

Investigating the Emergent Audio Classification Ability of ASR Foundation Models

Nov 15, 2023
Figure 1 for Investigating the Emergent Audio Classification Ability of ASR Foundation Models
Figure 2 for Investigating the Emergent Audio Classification Ability of ASR Foundation Models
Figure 3 for Investigating the Emergent Audio Classification Ability of ASR Foundation Models
Figure 4 for Investigating the Emergent Audio Classification Ability of ASR Foundation Models
Viaarxiv icon

Towards End-to-End Spoken Grammatical Error Correction

Nov 09, 2023
Viaarxiv icon

Zero-shot Audio Topic Reranking using Large Language Models

Sep 14, 2023
Figure 1 for Zero-shot Audio Topic Reranking using Large Language Models
Figure 2 for Zero-shot Audio Topic Reranking using Large Language Models
Figure 3 for Zero-shot Audio Topic Reranking using Large Language Models
Figure 4 for Zero-shot Audio Topic Reranking using Large Language Models
Viaarxiv icon

Mitigating Word Bias in Zero-shot Prompt-based Classifiers

Add code
Sep 10, 2023
Figure 1 for Mitigating Word Bias in Zero-shot Prompt-based Classifiers
Figure 2 for Mitigating Word Bias in Zero-shot Prompt-based Classifiers
Figure 3 for Mitigating Word Bias in Zero-shot Prompt-based Classifiers
Figure 4 for Mitigating Word Bias in Zero-shot Prompt-based Classifiers
Viaarxiv icon

Zero-shot NLG evaluation through Pairware Comparisons with LLMs

Add code
Jul 15, 2023
Figure 1 for Zero-shot NLG evaluation through Pairware Comparisons with LLMs
Figure 2 for Zero-shot NLG evaluation through Pairware Comparisons with LLMs
Figure 3 for Zero-shot NLG evaluation through Pairware Comparisons with LLMs
Figure 4 for Zero-shot NLG evaluation through Pairware Comparisons with LLMs
Viaarxiv icon

Adapting an ASR Foundation Model for Spoken Language Assessment

Add code
Jul 13, 2023
Figure 1 for Adapting an ASR Foundation Model for Spoken Language Assessment
Figure 2 for Adapting an ASR Foundation Model for Spoken Language Assessment
Figure 3 for Adapting an ASR Foundation Model for Spoken Language Assessment
Figure 4 for Adapting an ASR Foundation Model for Spoken Language Assessment
Viaarxiv icon