Ruby Teaming: Improving Quality Diversity Search with Memory for Automated Red Teaming
Paper
•
2406.11654
•
Published
•
6
Sabkuch Align Karo
university
AI & ML interests
None defined yet.
Recent Activity
View all activity
sabkuch-align-karo's activity
RishabhBhardwaj
authored
3
papers
3 months ago
RishabhBhardwaj
authored
a
paper
4 months ago
RishabhBhardwaj
authored
a
paper
5 months ago
RishabhBhardwaj
posted
an
update
6 months ago
Post
2128
Excited to announce the release of the community version of our guardrails: WalledGuard-C!
Feel free to use it—compared to Meta’s guardrails, it offers superior performance, being 4x faster. Most importantly, it's free for nearly any use!
Link: walledai/walledguard-c
#AISafety
Feel free to use it—compared to Meta’s guardrails, it offers superior performance, being 4x faster. Most importantly, it's free for nearly any use!
Link: walledai/walledguard-c
#AISafety
- 1 reply
RishabhBhardwaj
posted
an
update
6 months ago
Post
2437
🎉 We are thrilled to share our work on model merging. We proposed a new approach, Della-merging, which combines expert models from various domains into a single, versatile model. Della employs a magnitude-based sampling approach to eliminate redundant delta parameters, reducing interference when merging homologous models (those fine-tuned from the same backbone).
Della outperforms existing homologous model merging techniques such as DARE and TIES. Across three expert models (LM, Math, Code) and their corresponding benchmark datasets (AlpacaEval, GSM8K, MBPP), Della achieves an improvement of 3.6 points over TIES and 1.2 points over DARE.
Paper: DELLA-Merging: Reducing Interference in Model Merging through Magnitude-Based Sampling (2406.11617)
Github: https://github.com/declare-lab/della
@soujanyaporia @Tej3
Della outperforms existing homologous model merging techniques such as DARE and TIES. Across three expert models (LM, Math, Code) and their corresponding benchmark datasets (AlpacaEval, GSM8K, MBPP), Della achieves an improvement of 3.6 points over TIES and 1.2 points over DARE.
Paper: DELLA-Merging: Reducing Interference in Model Merging through Magnitude-Based Sampling (2406.11617)
Github: https://github.com/declare-lab/della
@soujanyaporia @Tej3
- 3 replies
RishabhBhardwaj
authored
4
papers
6 months ago
Recognizing Emotion Cause in Conversations
Paper
•
2012.11820
•
Published
Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment
Paper
•
2308.09662
•
Published
•
3
Language Models are Homer Simpson! Safety Re-Alignment of Fine-tuned Language Models through Task Arithmetic
Paper
•
2402.11746
•
Published
•
2
Language Model Unalignment: Parametric Red-Teaming to Expose Hidden Harms and Biases
Paper
•
2310.14303
•
Published
•
1
Xa9aX
authored
a
paper
8 months ago
deepanway
authored
6
papers
8 months ago
Tango 2: Aligning Diffusion-based Text-to-Audio Generations through Direct Preference Optimization
Paper
•
2404.09956
•
Published
•
11
Mustango: Toward Controllable Text-to-Music Generation
Paper
•
2311.08355
•
Published
MIME: MIMicking Emotions for Empathetic Response Generation
Paper
•
2010.01454
•
Published
Text-to-Audio Generation using Instruction-Tuned LLM and Latent Diffusion Model
Paper
•
2304.13731
•
Published
Multiview Contextual Commonsense Inference: A New Dataset and Task
Paper
•
2210.02890
•
Published
CICERO: A Dataset for Contextualized Commonsense Inference in Dialogues
Paper
•
2203.13926
•
Published
Xa9aX
authored
a
paper
9 months ago
Xa9aX
authored
a
paper
about 1 year ago