X-RiSAWOZ: High-Quality End-to-End Multilingual Dialogue Datasets and Few-shot Agents
Paper
•
2306.17674
•
Published
ponnurangam kumaraguru
pk-profgiri
AI & ML interests
AI Safety, Graphs, Machine unlearning, Interpretability, AI alignment, Applied ML & NLP
Recent Activity
authored
a paper
6 days ago
X-RiSAWOZ: High-Quality End-to-End Multilingual Dialogue Datasets and
Few-shot Agents
authored
a paper
6 days ago
HashSet -- A Dataset For Hashtag Segmentation
authored
a paper
6 days ago
Representation Surgery: Theory and Practice of Affine Steering
Organizations
None yet
pk-profgiri's activity
authored
11
papers
6 days ago
HashSet -- A Dataset For Hashtag Segmentation
Paper
•
2201.06741
•
Published
Representation Surgery: Theory and Practice of Affine Steering
Paper
•
2402.09631
•
Published
COBIAS: Contextual Reliability in Bias Assessment
Paper
•
2402.14889
•
Published
The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning
Paper
•
2403.03218
•
Published
•
1
Wu's Method can Boost Symbolic AI to Rival Silver Medalists and AlphaGeometry to Outperform Gold Medalists at IMO Geometry
Paper
•
2404.06405
•
Published
•
2
Benchmarks Underestimate the Readiness of Multi-lingual Dialogue Agents
Paper
•
2405.17840
•
Published
Counter Turing Test ($CT^2$): Investigating AI-Generated Text Detection for Hindi -- Ranking LLMs based on Hindi AI Detectability Index ($ADI_{hi}$)
Paper
•
2407.15694
•
Published
Exploring the Abilities of Large Language Models to Solve Proportional Analogies via Knowledge-Enhanced Prompting
Paper
•
2412.00869
•
Published
•
4
Rethinking Thinking Tokens: Understanding Why They Underperform in Practice
Paper
•
2411.11371
•
Published
Corrective Machine Unlearning
Paper
•
2402.14015
•
Published
authored
a
paper
8 days ago