AI Papers of the Week
Every paper worth reading in AI, hand-picked one week at a time.
PromptBench
A unified library for comprehensive evaluation and analysis of LLMs that consolidates multiple evaluation concerns under one roof.
Exploiting Novel GPT-4 APIs
A red-team study of three newer GPT-4 API surfaces - fine-tuning, function calling, and knowledge retrieval - that reveals each introduces new attack vectors.
Survey of Reasoning with Foundation Models
A comprehensive survey of reasoning with foundation models, covering tasks, methods, benchmarks, and future directions.
LLaRA
LLaRA adapts a decoder-only LLM for dense retrieval via two tailored pretext tasks that leverage text embeddings from the LLM itself.
Gemini's Language Abilities
CMU's impartial, reproducible evaluation of Gemini Pro against GPT and Mixtral across standard LLM benchmarks.
RAG for LLMs
A broad survey of Retrieval-Augmented Generation research, organizing the rapidly growing literature into a coherent map.
BabyLLM Challenge Findings
Reports results from a challenge on sample-efficient pretraining using a developmentally plausible corpus.
Mathematical LLMs Survey
A survey on the progress of LLMs on mathematical reasoning tasks, covering methods, benchmarks, and open problems.
LLM360
LLM360 is a framework for fully transparent open-source LLM development, with everything from data to training dynamics released.
LLMs in Medicine
A comprehensive survey (300+ papers) of LLMs applied to medicine, from clinical tasks to biomedical research.
Pearl
Meta's Pearl is a production-ready reinforcement learning agent package designed for real-world deployment constraints.
Gemini 1.0
Google launches Gemini 1.0, a multimodal family natively designed to reason across text, images, video, audio, and code from the ground up.
RankZephyr
RankZephyr is an open-source LLM for listwise zero-shot reranking that bridges the effectiveness gap with GPT-4.
Open-Source LLMs vs. ChatGPT
A survey cataloguing tasks where open-source LLMs claim to be on par with or better than ChatGPT.
MEDITRON-70B
EPFL's MEDITRON is an open-source family of medical LLMs at 7B and 70B parameters, continually pretrained on curated medical corpora.
Medprompt
Microsoft researchers show that careful prompt engineering can push general-purpose GPT-4 to state-of-the-art on medical benchmarks, no domain fine-tuning required.
UniIR
UniIR is a unified instruction-guided multimodal retriever that handles eight retrieval tasks across modalities with a single model.
Advancing Long-Context LLMs
A survey of methodologies for improving Transformer long-context capability across pretraining, fine-tuning, and inference stages.
Mirasol3B
Google's Mirasol3B is a multimodal model that decouples modalities into focused autoregressive components rather than forcing a single fused stream.
GPQA
A graduate-level Google-proof QA benchmark designed to stress-test reasoning in systems that might exceed human expertise.
GAIA
Meta's GAIA is a benchmark for general AI assistants that requires reasoning, multimodal handling, web browsing, and tool use to solve real-world questions.
MedAgents
A collaborative multi-round framework for medical reasoning that uses role-playing LLM agents to improve accuracy and reasoning depth.
TÜLU 2
Allen AI's TÜLU 2 is a suite of improved open instruction-tuned LLMs and an accompanying study of adaptation best practices.
Chain-of-Note (CoN)
Tencent's Chain-of-Note adds an explicit note-taking step to RAG so the model can evaluate retrieved evidence before answering.