Berkeley AI Research (BAIR)

Rethinking LLMs through the lens of world literature could revolutionize how AI interprets and engages with diverse cultural narratives.

D2D transforms conversational product search by cutting conversation times by nearly 30% while boosting accuracy and user satisfaction.

Local ordinances, often overlooked in legal AI, are now accessible at scale with the launch of LOCUS, enabling deep analysis of everyday regulations.

LLMs reveal surprising strengths and weaknesses in analyzing security logs, with performance heavily influenced by model design choices.

Stop hand-tuning your retrieval pipelines: BRANE slashes costs by up to 89% while matching accuracy by dynamically configuring pipelines per query.

Stop writing brittle log parsers: Sieve uses LLMs to directly query raw security logs with natural language, outperforming hand-coded scripts on complex investigations.

LLMs get *worse* at forecasting high-stakes events like epidemics and financial crises as they get more capable, because they aggressively extrapolate growth and overestimate tail risk.

YouTube's recommendation algorithm pushes Kyrgyz children towards Russian-language content, even when they signal a preference for their native tongue, effectively amplifying colonial influence.

LLMs struggle with structured 2D tasks when inputs are serialized into 1D, revealing a surprising performance gap compared to vision-augmented models that directly process the 2D layout.

LLMs are revolutionizing conversational AI research, and this survey offers a structured guide to navigating the rapidly evolving landscape of LLM-powered user simulation.

COMPASS outperforms traditional multilingual fine-tuning by effectively leveraging semantic gaps to enhance cross-lingual transfer and model adaptability.

Claim verification in peer reviews just got a major upgrade with Peerispect, a tool that highlights evidence directly in manuscripts for rapid assessment.

Current LLM detection methods in peer review are fooled by hybrid human-AI workflows, mistaking AI-written text for AI-originated ideas.

Generate diverse, physically plausible, and language-annotated whole-body motion data for humanoid robots at scale with this new interactive web-based pipeline.

Professional translators fear that LLMs are compromising the essential human elements of translation, potentially leading to harmful downstream consequences.

Reading Activity Traces (RATs) reveal the hidden creative work lost when algorithms automate interpretation, offering a path to design AI that preserves human insight.

Advisor performance paradoxically suffers most when personal AI is used moderately, highlighting the complex strategic interactions introduced by personal AI assistants.

Denoising diffusion models can significantly outperform discriminative methods in learning-to-rank, suggesting a new path for improving information retrieval.

LLMs evaluating job candidates exhibit significant bias against hedging language, docking candidates by 25.6% on average, even when the content is equivalent.

An LLM can analyze patient records like a clinician, predicting HIV care disengagement with clinically relevant justifications, potentially revolutionizing resource allocation and patient outcomes in sub-Saharan Africa.