Cyrus Rashtchian
@cyroid.bsky.social
Researcher at Google. Improving LLM factuality, RAG and multimodal alignment and evaluation. San Diego. he/him ☀️🌱🧗🏻🏐 Prev UCSD, MSR, UW, UIUC.
ICLR 2025 was so much fun!
April 28, 2025 at 3:55 AM
ICLR 2025 was so much fun!
Curious about fine-grained text-to-image model evaluation? Come see our spotlight paper on Gecko 🦎 in the afternoon poster session at #ICLR25
🏆Hall 3 + Hall 2B #359
🎖️Friday 3pm
ICLR: iclr.cc/virtual/2025...
Paper: arxiv.org/abs/2404.16820
Prompts: github.com/google-deepm...
🏆Hall 3 + Hall 2B #359
🎖️Friday 3pm
ICLR: iclr.cc/virtual/2025...
Paper: arxiv.org/abs/2404.16820
Prompts: github.com/google-deepm...
ICLR Poster Revisiting text-to-image evaluation with Gecko: on metrics, prompts, and human ratingICLR 2025
iclr.cc
April 25, 2025 at 1:45 AM
Curious about fine-grained text-to-image model evaluation? Come see our spotlight paper on Gecko 🦎 in the afternoon poster session at #ICLR25
🏆Hall 3 + Hall 2B #359
🎖️Friday 3pm
ICLR: iclr.cc/virtual/2025...
Paper: arxiv.org/abs/2404.16820
Prompts: github.com/google-deepm...
🏆Hall 3 + Hall 2B #359
🎖️Friday 3pm
ICLR: iclr.cc/virtual/2025...
Paper: arxiv.org/abs/2404.16820
Prompts: github.com/google-deepm...
Why do LLMs hallucinate with RAG?! 🤔
Find out at my #ICLR25 poster on Sufficient Context! 👋🏼
📍Hall 3 + Hall 2B #230
⏰ Fri 25 Apr 10 a.m. to 12:30 p.m.
Find out at my #ICLR25 poster on Sufficient Context! 👋🏼
📍Hall 3 + Hall 2B #230
⏰ Fri 25 Apr 10 a.m. to 12:30 p.m.
April 25, 2025 at 1:35 AM
Why do LLMs hallucinate with RAG?! 🤔
Find out at my #ICLR25 poster on Sufficient Context! 👋🏼
📍Hall 3 + Hall 2B #230
⏰ Fri 25 Apr 10 a.m. to 12:30 p.m.
Find out at my #ICLR25 poster on Sufficient Context! 👋🏼
📍Hall 3 + Hall 2B #230
⏰ Fri 25 Apr 10 a.m. to 12:30 p.m.
Happy to chat with anyone at ICLR about RAG, LLMs, Factuality!
I couldn't make it to ICLR this year but co-author @cyroid.bsky.social will be around to chat!
📄 Paper (ICLR ’25): arxiv.org/abs/2411.06037
💻 Key Findings & Prompts: github.com/hljoren/suff...
#RAG #ICLR2025
📄 Paper (ICLR ’25): arxiv.org/abs/2411.06037
💻 Key Findings & Prompts: github.com/hljoren/suff...
#RAG #ICLR2025
Sufficient Context: A New Lens on Retrieval Augmented Generation Systems
Augmenting LLMs with context leads to improved performance across many applications. Despite much research on Retrieval Augmented Generation (RAG) systems, an open question is whether errors arise bec...
arxiv.org
April 25, 2025 at 1:31 AM
Happy to chat with anyone at ICLR about RAG, LLMs, Factuality!
Reposted by Cyrus Rashtchian
When RAG systems hallucinate, is the LLM misusing available information or is the retrieved context insufficient? In our #ICLR2025 paper, we introduce "sufficient context" to disentangle these failure modes. Work w Jianyi Zhang, Chun-Sung Ferng, Da-Cheng Juan, Ankur Taly, @cyroid.bsky.social
April 24, 2025 at 6:18 PM
When RAG systems hallucinate, is the LLM misusing available information or is the retrieved context insufficient? In our #ICLR2025 paper, we introduce "sufficient context" to disentangle these failure modes. Work w Jianyi Zhang, Chun-Sung Ferng, Da-Cheng Juan, Ankur Taly, @cyroid.bsky.social
Reposted by Cyrus Rashtchian
1/2 Just a reminder about Google Research Scholar Program, providing up to $60K unrestricted gifts to recognize early-career professors and support world-class research at institutions around the world. This year, we are particularly interested in the following research areas...
Applications are open for the Google's Research Scholar Program, a program that supports early-career professors conducting research in fields relevant to Google. Learn more and apply by January 27 at goo.gle/RS
Research scholar program
Overview
goo.gle
December 20, 2024 at 7:04 PM
1/2 Just a reminder about Google Research Scholar Program, providing up to $60K unrestricted gifts to recognize early-career professors and support world-class research at institutions around the world. This year, we are particularly interested in the following research areas...
Longer thread about our new factuality decoding method SLED at NeurIPS 2024. Main idea: freeze the model, but be thoughtful about the decoding. With a small amount of extra inference-time compute, we increase accuracy by 3% on several benchmarks! SLED helps for all major open source models!
December 13, 2024 at 6:43 PM
Longer thread about our new factuality decoding method SLED at NeurIPS 2024. Main idea: freeze the model, but be thoughtful about the decoding. With a small amount of extra inference-time compute, we increase accuracy by 3% on several benchmarks! SLED helps for all major open source models!
First shameless plug -- our new factuality decoding method, SLED gets SOTA improvements on 14+ models (Llama 2/3, Gemma, Mistral) & 9 benchmarks!
See our #NeurIPS2024 poster today (Friday) in the East Exhibit Hall A-C #3311
See our #NeurIPS2024 poster today (Friday) in the East Exhibit Hall A-C #3311
December 13, 2024 at 5:55 PM
First shameless plug -- our new factuality decoding method, SLED gets SOTA improvements on 14+ models (Llama 2/3, Gemma, Mistral) & 9 benchmarks!
See our #NeurIPS2024 poster today (Friday) in the East Exhibit Hall A-C #3311
See our #NeurIPS2024 poster today (Friday) in the East Exhibit Hall A-C #3311
Reposted by Cyrus Rashtchian
Hi friends!🩷
I have never done this but i’m making a list so and i can keep in touch with all of you more easily🫶🏻
please like this or say hi if i can add you🥰 Thank🫶🏻
I have never done this but i’m making a list so and i can keep in touch with all of you more easily🫶🏻
please like this or say hi if i can add you🥰 Thank🫶🏻
December 2, 2024 at 9:51 PM
Hi friends!🩷
I have never done this but i’m making a list so and i can keep in touch with all of you more easily🫶🏻
please like this or say hi if i can add you🥰 Thank🫶🏻
I have never done this but i’m making a list so and i can keep in touch with all of you more easily🫶🏻
please like this or say hi if i can add you🥰 Thank🫶🏻
Reposted by Cyrus Rashtchian
Everyone I spoke to at @rl-conference.bsky.social last summer agreed on it being one of the best conferences ever for an RL researcher... So many great RL-focused papers!
CFP is out, send your work here!
CFP is out, send your work here!
The call for papers for RLC is now up! Abstract deadline of 2/14, submission deadline of 2/21!
Please help us spread the word.
rl-conference.cc/callforpaper...
Please help us spread the word.
rl-conference.cc/callforpaper...
RLJ | RLC Call for Papers
rl-conference.cc
December 2, 2024 at 4:02 PM
Everyone I spoke to at @rl-conference.bsky.social last summer agreed on it being one of the best conferences ever for an RL researcher... So many great RL-focused papers!
CFP is out, send your work here!
CFP is out, send your work here!
Excited to try out bluesky and chat about GenAI and ML theory!
December 2, 2024 at 6:32 PM
Excited to try out bluesky and chat about GenAI and ML theory!