Chain-of-thought prompting, by including intermediate reasoning steps in few-shot examples, elicits strong reasoning abilities in large language models on arithmetic, commonsense, and symbolic tasks.
hub Canonical reference
arXiv preprint arXiv:2107.13586 , year=
Canonical reference. 86% of citing Pith papers cite this work as background.
18
Pith papers citing it
Background
86% of classified citations
hub tools
citation-role summary
background 6
method 1
citation-polarity summary
representative citing papers
PAL improves few-shot reasoning accuracy by having LLMs generate executable programs rather than text-based chains of thought, outperforming much larger models on math and logic benchmarks.
Semantic geometry emerges transiently early in next-token prediction training before collapsing to Neural Collapse symmetry in synthetic settings with latent semantic factors.
Self-Harness lets LLM agents autonomously refine their interaction harnesses through weakness mining, proposal generation, and validation, raising held-out pass rates on Terminal-Bench-2.0 from 40.5% to 61.9%, 23.8% to 38.1%, and 42.9% to 57.1% across three models.
ToGRL learns high-quality graph structures from raw heterogeneous graphs via a two-stage topology extraction process and prompt tuning, outperforming prior methods on five datasets.
SkVM uses capability profiling and compiler-style techniques to make skills portable across LLMs and harnesses, raising task completion rates while cutting token use by up to 40% and delivering up to 3.2x speedup.
OPT releases open decoder-only transformers up to 175B parameters that match GPT-3 performance at one-seventh the carbon cost, along with code and training logs.
Presents the NATURAL INSTRUCTIONS meta-dataset and shows generative pre-trained language models achieve 19% better generalization to unseen tasks when using task instructions.
CRAFT is a Pareto-front prompt optimizer that allocates scarce LLM validation calls to candidates near the current front using accuracy- and cost-oriented generators plus NSGA-II retention.
CrysLDNet combines VAE and latent diffusion pretraining on unlabeled crystals to improve graph encoder performance on property prediction by about 4-5% on JARVIS and MP datasets.
PEML co-optimizes continuous prompts and low-rank adaptations to deliver up to 6.67% average accuracy gains over existing multi-task PEFT methods on GLUE, SuperGLUE, and other benchmarks.
A unified framework for LLM agent memory is benchmarked, with a new hybrid method outperforming state-of-the-art on standard tasks.
A multi-agent AI system generates novel biomedical hypotheses that show promising experimental validation in drug repurposing for leukemia, new targets for liver fibrosis, and a bacterial gene transfer mechanism.
Med-PaLM 2 achieves 86.5% accuracy on MedQA and approaches or exceeds prior state-of-the-art on other medical QA benchmarks while receiving higher physician preference ratings than human answers on consumer questions.
STELLAR-E modifies the TGRT Self-Instruct framework to produce tailored synthetic LLM evaluation datasets that score an average 5.7% higher on LLM-as-a-judge metrics than existing language-specific benchmarks.
LLMs classify Gaza War headlines as strongly negative while fine-tuned Arabic BERT models favor neutral labels, producing measurable non-random divergences in sentiment distributions.
PaLM 2 reports state-of-the-art results on language, reasoning, and multilingual tasks with improved efficiency over PaLM.
Systematic review of 145 papers on LLM-based log analysis, providing a unified taxonomy, common design patterns, evaluation practices, and challenges for deployment under drift and limited labels.
citing papers explorer
-
Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
Chain-of-thought prompting, by including intermediate reasoning steps in few-shot examples, elicits strong reasoning abilities in large language models on arithmetic, commonsense, and symbolic tasks.
-
PAL: Program-aided Language Models
PAL improves few-shot reasoning accuracy by having LLMs generate executable programs rather than text-based chains of thought, outperforming much larger models on math and logic benchmarks.
-
Structure Before Collapse: Transient semantic geometry in next-token prediction
Semantic geometry emerges transiently early in next-token prediction training before collapsing to Neural Collapse symmetry in synthetic settings with latent semantic factors.
-
Self-Harness: Harnesses That Improve Themselves
Self-Harness lets LLM agents autonomously refine their interaction harnesses through weakness mining, proposal generation, and validation, raising held-out pass rates on Terminal-Bench-2.0 from 40.5% to 61.9%, 23.8% to 38.1%, and 42.9% to 57.1% across three models.
-
Graph Topology Information Enhanced Heterogeneous Graph Representation Learning
ToGRL learns high-quality graph structures from raw heterogeneous graphs via a two-stage topology extraction process and prompt tuning, outperforming prior methods on five datasets.
-
SkVM: Revisiting Language VM for Skills across Heterogenous LLMs and Harnesses
SkVM uses capability profiling and compiler-style techniques to make skills portable across LLMs and harnesses, raising task completion rates while cutting token use by up to 40% and delivering up to 3.2x speedup.
-
OPT: Open Pre-trained Transformer Language Models
OPT releases open decoder-only transformers up to 175B parameters that match GPT-3 performance at one-seventh the carbon cost, along with code and training logs.
-
Cross-Task Generalization via Natural Language Crowdsourcing Instructions
Presents the NATURAL INSTRUCTIONS meta-dataset and shows generative pre-trained language models achieve 19% better generalization to unseen tasks when using task instructions.
-
CRAFT: Cost-aware Refinement And Front-aware Tuning of Prompts
CRAFT is a Pareto-front prompt optimizer that allocates scarce LLM validation calls to candidates near the current front using accuracy- and cost-oriented generators plus NSGA-II retention.
-
Latent Diffusion Pretraining for Crystal Property Prediction
CrysLDNet combines VAE and latent diffusion pretraining on unlabeled crystals to improve graph encoder performance on property prediction by about 4-5% on JARVIS and MP datasets.
-
PEML: Parameter-efficient Multi-Task Learning with Optimized Continuous Prompts
PEML co-optimizes continuous prompts and low-rank adaptations to deliver up to 6.67% average accuracy gains over existing multi-task PEFT methods on GLUE, SuperGLUE, and other benchmarks.
-
Memory in the LLM Era: Modular Architectures and Strategies in a Unified Framework
A unified framework for LLM agent memory is benchmarked, with a new hybrid method outperforming state-of-the-art on standard tasks.
-
Towards an AI co-scientist
A multi-agent AI system generates novel biomedical hypotheses that show promising experimental validation in drug repurposing for leukemia, new targets for liver fibrosis, and a bacterial gene transfer mechanism.
-
Towards Expert-Level Medical Question Answering with Large Language Models
Med-PaLM 2 achieves 86.5% accuracy on MedQA and approaches or exceeds prior state-of-the-art on other medical QA benchmarks while receiving higher physician preference ratings than human answers on consumer questions.
-
STELLAR-E: a Synthetic, Tailored, End-to-end LLM Application Rigorous Evaluator
STELLAR-E modifies the TGRT Self-Instruct framework to produce tailored synthetic LLM evaluation datasets that score an average 5.7% higher on LLM-as-a-judge metrics than existing language-specific benchmarks.
-
Sentiment Classification of Gaza War Headlines: A Comparative Analysis of Large Language Models and Arabic Fine-Tuned BERT Models
LLMs classify Gaza War headlines as strongly negative while fine-tuned Arabic BERT models favor neutral labels, producing measurable non-random divergences in sentiment distributions.
-
PaLM 2 Technical Report
PaLM 2 reports state-of-the-art results on language, reasoning, and multilingual tasks with improved efficiency over PaLM.
-
LLM4Log: A Systematic Review of Large Language Model-based Log Analysis
Systematic review of 145 papers on LLM-based log analysis, providing a unified taxonomy, common design patterns, evaluation practices, and challenges for deployment under drift and limited labels.