Picture for Patrick Lewis

Patrick Lewis

FLARE: Faithful Logic-Aided Reasoning and Exploration

Add code
Oct 14, 2024
Figure 1 for FLARE: Faithful Logic-Aided Reasoning and Exploration
Figure 2 for FLARE: Faithful Logic-Aided Reasoning and Exploration
Figure 3 for FLARE: Faithful Logic-Aided Reasoning and Exploration
Figure 4 for FLARE: Faithful Logic-Aided Reasoning and Exploration
Viaarxiv icon

ALR$^2$: A Retrieve-then-Reason Framework for Long-context Question Answering

Add code
Oct 04, 2024
Figure 1 for ALR$^2$: A Retrieve-then-Reason Framework for Long-context Question Answering
Figure 2 for ALR$^2$: A Retrieve-then-Reason Framework for Long-context Question Answering
Figure 3 for ALR$^2$: A Retrieve-then-Reason Framework for Long-context Question Answering
Figure 4 for ALR$^2$: A Retrieve-then-Reason Framework for Long-context Question Answering
Viaarxiv icon

Replacing Judges with Juries: Evaluating LLM Generations with a Panel of Diverse Models

Add code
May 01, 2024
Viaarxiv icon

SnapKV: LLM Knows What You are Looking for Before Generation

Add code
Apr 22, 2024
Figure 1 for SnapKV: LLM Knows What You are Looking for Before Generation
Figure 2 for SnapKV: LLM Knows What You are Looking for Before Generation
Figure 3 for SnapKV: LLM Knows What You are Looking for Before Generation
Figure 4 for SnapKV: LLM Knows What You are Looking for Before Generation
Viaarxiv icon

From One to Many: Expanding the Scope of Toxicity Mitigation in Language Models

Add code
Mar 06, 2024
Figure 1 for From One to Many: Expanding the Scope of Toxicity Mitigation in Language Models
Figure 2 for From One to Many: Expanding the Scope of Toxicity Mitigation in Language Models
Figure 3 for From One to Many: Expanding the Scope of Toxicity Mitigation in Language Models
Figure 4 for From One to Many: Expanding the Scope of Toxicity Mitigation in Language Models
Viaarxiv icon

MultiContrievers: Analysis of Dense Retrieval Representations

Add code
Feb 24, 2024
Viaarxiv icon

Rank-without-GPT: Building GPT-Independent Listwise Rerankers on Open-Source Large Language Models

Add code
Dec 05, 2023
Figure 1 for Rank-without-GPT: Building GPT-Independent Listwise Rerankers on Open-Source Large Language Models
Figure 2 for Rank-without-GPT: Building GPT-Independent Listwise Rerankers on Open-Source Large Language Models
Figure 3 for Rank-without-GPT: Building GPT-Independent Listwise Rerankers on Open-Source Large Language Models
Figure 4 for Rank-without-GPT: Building GPT-Independent Listwise Rerankers on Open-Source Large Language Models
Viaarxiv icon

Goodtriever: Adaptive Toxicity Mitigation with Retrieval-augmented Models

Add code
Oct 11, 2023
Viaarxiv icon

On the Challenges of Using Black-Box APIs for Toxicity Evaluation in Research

Add code
Apr 24, 2023
Viaarxiv icon

Mini-Model Adaptation: Efficiently Extending Pretrained Models to New Languages via Aligned Shallow Training

Add code
Dec 20, 2022
Viaarxiv icon