RT @valeriechen_: Do benchmark improvements translate into downstream developer productivity? . In our latest #TMLR paper, we run a study w….

RT @venturetwins: I find these "tiny people doing things" videos so calming

Nice article discussing Deepseek and the evolving landscape for AI players!.

RT @kalyan_kpl: Granite Guardian (Safeguard LLMs). This paper introduces the Granite Guardian models, a suite of safeguard LLMs. Granite….

RT @kalyan_kpl: Top LLM Papers of the Week (December Week 2, 2024). [1] EXAONE 3.5 (Open LLMs for Real-world use cases).[2] Granite Guardia….

RT @Marktechpost: IBM Open-Sources Granite Guardian: A Suite of Safeguards for Risk Detection in LLMs. IBM has introduced Granite Guardian,….

RT @rohanpaul_ai: A single model that spots everything from toxic prompts to RAG hallucinations in LLM interactions. Granite Guardian intr….

RT @krvarshney: Look at those beautiful Granite Guardian safety vests! #brand #bootleg. The Granite Guardian technical report is now on arX….

RT @dair_ai: 10). Granite Guardian - IBM open-sources Granite Guardian, a suite of safeguards for risk detection in LLMs. .

RT @omarsar0: IBM open-sources Granite Guardian, a suite of safeguards for risk detection in LLMs. The authors claim that "With AUC scores….

Learn about other exciting work from our group from @krvarshney's blog:

Adversarial Prompt Evaluation: Guardrails benchmark will be presented by Giulio Zizzo at the Safe Generative AI, Dec 15th).Github:

Attack Atlas: Red-teaming taxonomy (Poster @ Red Teaming GenAI, Dec 14th) with @iambrishing et. al. arxiv:

More safety research at #NeurIPS2024 workshops:. Value Alignment from Unstructured Text (Poster @ Pluralistic Alignment, Dec 14th) work led by Inkit Padhi with @nrkarthikeyan, @mnagired , Pierre Dognin,@krvarshney .arxiv:

Catch up with @yufanghou to learn more about the new LLM reliability benchmark - "WikiContradict: A Benchmark for Evaluating LLMs on Real-World Knowledge Conflicts from Wikipedia".arxiv: 📍Th, Dec 12, 14:00 EST Poster Session 3 East.

"Interventional Causal Discovery in a Mixture of DAGs" with Dmitriy Katz, Dennis Wei, @satajer .arxiv: 📍Th, Dec 12, 19:30 EST Poster Session 4 West.

Two excellent papers led by @VariciBurak on causality!."Causal Bandits for Linear Structural Equation Models" with Karthikeyan shanmugam, @satajer.arxiv: 📍We, Dec 11, 19:30 EST Poster Session 2 West.

Exciting work led by Mingjian Jiang on "Graph-based Uncertainty Metrics for Long-form LLM Generations" with @YangjunR, Salim Roukos, @tatsu_hashimoto .arxiv: 📍Th, Dec 12, 14:00 EST Poster Session 3 East.

Learn from @maohaos2 about our paper - "Are Uncertainty Quantification Capabilities of Evidential Deep Learning a Mirage?" with Jongha Ryu, @soumy_aghosh , Bu Yuheng, Subhro Das, Greg Wornell.arxiv: 📍Th, Dec 12, 14:00 EST Poster Session 3 East.

Additional code/demo links:.@ollama - cookbook - @nvidia NIM hosted demo -