SPARE-PRM
Collection
Process Reward Models (PRMs) trained using Single-Pass Annotation with Reference-Guided Evaluation (SPARE) methodology proposed in our AAAI-2026 paper
•
2 items
•
Updated
AI & ML interests
The Ubiquitous Knowledge Processing Lab researches natural language processing, text mining, eLearning, and digital humanities.
Recent Activity
View all activity
imbesat-rizvi
updated
a
collection
17 days ago
timbmg
authored
a
paper
4 months ago
imbesat-rizvi
updated
a
model
5 months ago
imbesat-rizvi
published
a
model
5 months ago
haritzpuerto
authored
2
papers
6 months ago
imbesat-rizvi
updated
a
model
7 months ago
imbesat-rizvi
updated
a
dataset
7 months ago
imbesat-rizvi
published
a
model
7 months ago
iNeil77
authored
a
paper
7 months ago
haritzpuerto
posted
an
update
7 months ago
Post
366
📜 Accepted at ACL 2025! Fine-Tuning on Diverse Reasoning Chains Drives Within-Inference CoT Refinement in LLMs
We propose to fine-tune LLMs to generate diverse chains of thought (DCoT) in a single inference step. This enables within-inference refinement of the cots, no external feedback needed!
🔗 https://arxiv.org/abs/2407.03181
We propose to fine-tune LLMs to generate diverse chains of thought (DCoT) in a single inference step. This enables within-inference refinement of the cots, no external feedback needed!
🔗 https://arxiv.org/abs/2407.03181
Rachneet
updated
a
dataset
7 months ago
Rachneet
published
a
dataset
7 months ago
timbmg
updated
a
dataset
8 months ago
sukannya
authored
2
papers
9 months ago
iNeil77
authored
3
papers
9 months ago
EMMA-500: Enhancing Massively Multilingual Adaptation of Large Language Models
Paper
•
2409.17892
•
Published
•
2
ObscuraCoder: Powering Efficient Code LM Pre-Training Via Obfuscation Grounding
Paper
•
2504.00019
•
Published
IRCoder: Intermediate Representations Make Language Models Robust Multilingual Code Generators
Paper
•
2403.03894
•
Published