Picture for Shafiq Joty

Shafiq Joty

Preference Optimization for Reasoning with Pseudo Feedback

Add code
Nov 25, 2024
Viaarxiv icon

Investigating Factuality in Long-Form Text Generation: The Roles of Self-Known and Self-Unknown

Add code
Nov 24, 2024
Figure 1 for Investigating Factuality in Long-Form Text Generation: The Roles of Self-Known and Self-Unknown
Figure 2 for Investigating Factuality in Long-Form Text Generation: The Roles of Self-Known and Self-Unknown
Figure 3 for Investigating Factuality in Long-Form Text Generation: The Roles of Self-Known and Self-Unknown
Figure 4 for Investigating Factuality in Long-Form Text Generation: The Roles of Self-Known and Self-Unknown
Viaarxiv icon

On Positional Bias of Faithfulness for Long-form Summarization

Add code
Oct 31, 2024
Figure 1 for On Positional Bias of Faithfulness for Long-form Summarization
Figure 2 for On Positional Bias of Faithfulness for Long-form Summarization
Figure 3 for On Positional Bias of Faithfulness for Long-form Summarization
Figure 4 for On Positional Bias of Faithfulness for Long-form Summarization
Viaarxiv icon

JudgeRank: Leveraging Large Language Models for Reasoning-Intensive Reranking

Add code
Oct 31, 2024
Viaarxiv icon

P-FOLIO: Evaluating and Improving Logical Reasoning with Abundant Human-Written Reasoning Chains

Add code
Oct 11, 2024
Figure 1 for P-FOLIO: Evaluating and Improving Logical Reasoning with Abundant Human-Written Reasoning Chains
Figure 2 for P-FOLIO: Evaluating and Improving Logical Reasoning with Abundant Human-Written Reasoning Chains
Figure 3 for P-FOLIO: Evaluating and Improving Logical Reasoning with Abundant Human-Written Reasoning Chains
Figure 4 for P-FOLIO: Evaluating and Improving Logical Reasoning with Abundant Human-Written Reasoning Chains
Viaarxiv icon

ReIFE: Re-evaluating Instruction-Following Evaluation

Add code
Oct 09, 2024
Figure 1 for ReIFE: Re-evaluating Instruction-Following Evaluation
Figure 2 for ReIFE: Re-evaluating Instruction-Following Evaluation
Figure 3 for ReIFE: Re-evaluating Instruction-Following Evaluation
Figure 4 for ReIFE: Re-evaluating Instruction-Following Evaluation
Viaarxiv icon

Can We Further Elicit Reasoning in LLMs? Critic-Guided Planning with Retrieval-Augmentation for Solving Challenging Tasks

Add code
Oct 02, 2024
Viaarxiv icon

Open-RAG: Enhanced Retrieval-Augmented Reasoning with Open-Source Large Language Models

Add code
Oct 02, 2024
Viaarxiv icon

Discovering the Gems in Early Layers: Accelerating Long-Context LLMs with 1000x Input Token Reduction

Add code
Sep 25, 2024
Figure 1 for Discovering the Gems in Early Layers: Accelerating Long-Context LLMs with 1000x Input Token Reduction
Figure 2 for Discovering the Gems in Early Layers: Accelerating Long-Context LLMs with 1000x Input Token Reduction
Figure 3 for Discovering the Gems in Early Layers: Accelerating Long-Context LLMs with 1000x Input Token Reduction
Figure 4 for Discovering the Gems in Early Layers: Accelerating Long-Context LLMs with 1000x Input Token Reduction
Viaarxiv icon

Direct Judgement Preference Optimization

Add code
Sep 23, 2024
Figure 1 for Direct Judgement Preference Optimization
Figure 2 for Direct Judgement Preference Optimization
Figure 3 for Direct Judgement Preference Optimization
Figure 4 for Direct Judgement Preference Optimization
Viaarxiv icon