Picture for Archiki Prasad

Archiki Prasad

LASeR: Learning to Adaptively Select Reward Models with Multi-Armed Bandits

Add code
Oct 02, 2024
Viaarxiv icon

MAgICoRe: Multi-Agent, Iterative, Coarse-to-Fine Refinement for Reasoning

Add code
Sep 18, 2024
Viaarxiv icon

AdaCAD: Adaptively Decoding to Balance Conflicts between Contextual and Parametric Knowledge

Add code
Sep 11, 2024
Viaarxiv icon

System-1.x: Learning to Balance Fast and Slow Planning with Language Models

Add code
Jul 19, 2024
Viaarxiv icon

Soft Self-Consistency Improves Language Model Agents

Add code
Feb 20, 2024
Viaarxiv icon

ReGAL: Refactoring Programs to Discover Generalizable Abstractions

Add code
Jan 29, 2024
Viaarxiv icon

ADaPT: As-Needed Decomposition and Planning with Language Models

Add code
Nov 08, 2023
Viaarxiv icon

Rephrase, Augment, Reason: Visual Grounding of Questions for Vision-Language Models

Add code
Oct 09, 2023
Viaarxiv icon

ReCEval: Evaluating Reasoning Chains via Correctness and Informativeness

Add code
Apr 21, 2023
Viaarxiv icon

GrIPS: Gradient-free, Edit-based Instruction Search for Prompting Large Language Models

Add code
Mar 14, 2022
Figure 1 for GrIPS: Gradient-free, Edit-based Instruction Search for Prompting Large Language Models
Figure 2 for GrIPS: Gradient-free, Edit-based Instruction Search for Prompting Large Language Models
Figure 3 for GrIPS: Gradient-free, Edit-based Instruction Search for Prompting Large Language Models
Figure 4 for GrIPS: Gradient-free, Edit-based Instruction Search for Prompting Large Language Models
Viaarxiv icon