BEHAVIOR-1K introduces a benchmark of 1,000 human everyday activities in realistic simulated scenes together with the OMNIGIBSON physics simulator to evaluate embodied AI.
hub Mixed citations
SQuAD: 100,000+ Questions for Machine Comprehension of Text
Mixed citation behavior. Most common role is background (58%).
85
Pith papers citing it
Background
58% of classified citations
abstract
We present the Stanford Question Answering Dataset (SQuAD), a new reading comprehension dataset consisting of 100,000+ questions posed by crowdworkers on a set of Wikipedia articles, where the answer to each question is a segment of text from the corresponding reading passage. We analyze the dataset to understand the types of reasoning required to answer the questions, leaning heavily on dependency and constituency trees. We build a strong logistic regression model, which achieves an F1 score of 51.0%, a significant improvement over a simple baseline (20%). However, human performance (86.8%) is much higher, indicating that the dataset presents a good challenge problem for future research. The dataset is freely available at https://stanford-qa.com
hub tools
citation-role summary
background 7
dataset 5
citation-polarity summary
claims ledger
- abstract We present the Stanford Question Answering Dataset (SQuAD), a new reading comprehension dataset consisting of 100,000+ questions posed by crowdworkers on a set of Wikipedia articles, where the answer to each question is a segment of text from the corresponding reading passage. We analyze the dataset to understand the types of reasoning required to answer the questions, leaning heavily on dependency and constituency trees. We build a strong logistic regression model, which achieves an F1 score of 51.0%, a significant improvement over a simple baseline (20%). However, human performance (86.8%) i
co-cited works
representative citing papers
An unsupervised technique extracts latent yes-no knowledge from language model activations by locating a direction that satisfies logical consistency properties, outperforming zero-shot accuracy by 4% on average across models and datasets.
Fine-tuning BERT for query-passage relevance classification achieves state-of-the-art results on TREC-CAR and MS MARCO, with a 27% relative gain in MRR@10 over prior methods.
TCD-Arena is a new customizable testing framework that runs millions of experiments to map how 33 different assumption violations affect time series causal discovery methods and shows ensembles can boost overall robustness.
Deep-Reporter introduces a unified agentic framework for grounded multimodal long-form generation via multimodal search, checklist-guided synthesis, and recurrent context management, plus the M2LongBench benchmark.
LLM DNA is introduced as a low-dimensional bi-Lipschitz functional representation proven to satisfy inheritance and genetic determinism, with a training-free extraction pipeline tested on 305 models to reveal relationships and construct phylogenetic trees.
VocabTailor introduces a decoupled dynamic vocabulary selection framework that reduces vocabulary-related memory in SLMs by up to 99% with minimal task performance loss.
A survey that defines Compound AI Systems, proposes a multi-dimensional taxonomy based on component roles and orchestration strategies, reviews four foundational paradigms, and identifies key challenges for future research.
LLaMA-Adapter turns frozen LLaMA 7B into a capable instruction follower using only 1.2M new parameters and zero-init attention, matching Alpaca while extending to image-conditioned reasoning on ScienceQA and COCO.
Multitask fine-tuning of an encoder-decoder model on prompted datasets produces zero-shot generalization that often beats models up to 16 times larger on standard benchmarks.
Switch Transformers use top-1 expert routing in a Mixture of Experts setup to scale to trillion-parameter language models with constant compute and up to 4x speedup over T5-XXL.
BART introduces a denoising pretraining method for seq2seq models that matches RoBERTa on GLUE and SQuAD while setting new state-of-the-art results on abstractive summarization, dialogue, and QA with up to 6 ROUGE gains.
T5 casts all NLP tasks as text-to-text generation, systematically explores pre-training choices, and reaches strong performance on summarization, QA, classification and other tasks via large-scale training on the Colossal Clean Crawled Corpus.
PubMedQA supplies 273k+ biomedical QA instances that require reasoning over research abstracts to produce yes/no/maybe answers.
XLNet is a generalized autoregressive pretraining method that learns bidirectional contexts via permutation-based factorization and outperforms BERT on 20 NLP tasks.
MS MARCO is a new large-scale machine reading comprehension dataset built from real Bing search queries, human-generated answers, and web passages, supporting three tasks including answer synthesis and passage ranking.
Data-similarity and data-influence produce significantly overlapping rankings of training documents for LLM outputs, with asymmetry allowing a favorable cost-accuracy trade-off.
SHIFT mitigates language bias in MLIR by subtracting estimated relative language vectors from document embeddings during indexing using parallel translation pairs.
MCompassRAG adds topic metadata to chunk representations and uses LLM distillation to train a lightweight topic-aware retriever, reporting 8.24% average information efficiency gain and over 5x lower latency than strong baselines across six benchmarks.
ProactiveLLM enables active interaction in streaming LLMs by learning semantic sufficiency cues from partial inputs through mask-based modeling and synchronized privileged self-distillation without external supervision.
EmbGen creates synthetic QA data by entity decomposition, embedding-based reassembly into clusters, and multi-level sampling with cluster-specific prompts, yielding up to 88.9% higher Binary Accuracy than baselines on heterogeneous datasets under fixed token budgets.
MAFIG is a multi-agent framework that uses LLM agents and evaluators to generate reading comprehension items with significantly higher adherence to specified feature constraints than single-agent baselines.
ProxyKV offloads KV cache importance scoring to a lightweight intra-family small-model proxy with HybridAxialMapper and ranking-focused loss, matching KVZip accuracy while achieving up to 3.21x prefilling speedup on models up to 32B.
PragLocker generates function-preserving but non-portable prompts for LLM agents via code-symbol semantic anchoring followed by target-model feedback noise injection.
citing papers explorer
-
BEHAVIOR-1K: A Human-Centered, Embodied AI Benchmark with 1,000 Everyday Activities and Realistic Simulation
BEHAVIOR-1K introduces a benchmark of 1,000 human everyday activities in realistic simulated scenes together with the OMNIGIBSON physics simulator to evaluate embodied AI.
-
Discovering Latent Knowledge in Language Models Without Supervision
An unsupervised technique extracts latent yes-no knowledge from language model activations by locating a direction that satisfies logical consistency properties, outperforming zero-shot accuracy by 4% on average across models and datasets.
-
Passage Re-ranking with BERT
Fine-tuning BERT for query-passage relevance classification achieves state-of-the-art results on TREC-CAR and MS MARCO, with a 27% relative gain in MRR@10 over prior methods.
-
TCD-Arena: Assessing Robustness of Time Series Causal Discovery Methods Against Assumption Violations
TCD-Arena is a new customizable testing framework that runs millions of experiments to map how 33 different assumption violations affect time series causal discovery methods and shows ensembles can boost overall robustness.
-
Deep-Reporter: Deep Research for Grounded Multimodal Long-Form Generation
Deep-Reporter introduces a unified agentic framework for grounded multimodal long-form generation via multimodal search, checklist-guided synthesis, and recurrent context management, plus the M2LongBench benchmark.
-
LLM DNA: Tracing Model Evolution via Functional Representations
LLM DNA is introduced as a low-dimensional bi-Lipschitz functional representation proven to satisfy inheritance and genetic determinism, with a training-free extraction pipeline tested on 305 models to reveal relationships and construct phylogenetic trees.
-
VocabTailor: Dynamic Vocabulary Selection for Downstream Tasks in Small Language Models
VocabTailor introduces a decoupled dynamic vocabulary selection framework that reduces vocabulary-related memory in SLMs by up to 99% with minimal task performance loss.
-
From Standalone LLMs to Integrated Intelligence: A Survey of Compound Al Systems
A survey that defines Compound AI Systems, proposes a multi-dimensional taxonomy based on component roles and orchestration strategies, reviews four foundational paradigms, and identifies key challenges for future research.
-
LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention
LLaMA-Adapter turns frozen LLaMA 7B into a capable instruction follower using only 1.2M new parameters and zero-init attention, matching Alpaca while extending to image-conditioned reasoning on ScienceQA and COCO.
-
Multitask Prompted Training Enables Zero-Shot Task Generalization
Multitask fine-tuning of an encoder-decoder model on prompted datasets produces zero-shot generalization that often beats models up to 16 times larger on standard benchmarks.
-
Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity
Switch Transformers use top-1 expert routing in a Mixture of Experts setup to scale to trillion-parameter language models with constant compute and up to 4x speedup over T5-XXL.
-
BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension
BART introduces a denoising pretraining method for seq2seq models that matches RoBERTa on GLUE and SQuAD while setting new state-of-the-art results on abstractive summarization, dialogue, and QA with up to 6 ROUGE gains.
-
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
T5 casts all NLP tasks as text-to-text generation, systematically explores pre-training choices, and reaches strong performance on summarization, QA, classification and other tasks via large-scale training on the Colossal Clean Crawled Corpus.
-
PubMedQA: A Dataset for Biomedical Research Question Answering
PubMedQA supplies 273k+ biomedical QA instances that require reasoning over research abstracts to produce yes/no/maybe answers.
-
XLNet: Generalized Autoregressive Pretraining for Language Understanding
XLNet is a generalized autoregressive pretraining method that learns bidirectional contexts via permutation-based factorization and outperforms BERT on 20 NLP tasks.
-
MS MARCO: A Human Generated MAchine Reading COmprehension Dataset
MS MARCO is a new large-scale machine reading comprehension dataset built from real Bing search queries, human-generated answers, and web passages, supporting three tasks including answer synthesis and passage ranking.
-
Quantifying the Agreement Between Data-Influence and Data-Similarity to Understand LLM Behavior
Data-similarity and data-influence produce significantly overlapping rankings of training documents for LLM outputs, with asymmetry allowing a favorable cost-accuracy trade-off.
-
SHIFT: Semantic Harmonization via Index-side Feature Transformation for Multilingual Information Retrieval
SHIFT mitigates language bias in MLIR by subtracting estimated relative language vectors from document embeddings during indexing using parallel translation pairs.
-
MCompassRAG: Topic Metadata as a Semantic Compass for Paragraph-Level Retrieval
MCompassRAG adds topic metadata to chunk representations and uses LLM distillation to train a lightweight topic-aware retriever, reporting 8.24% average information efficiency gain and over 5x lower latency than strong baselines across six benchmarks.
-
ProactiveLLM: Learning Active Interaction for Streaming Large Language Models
ProactiveLLM enables active interaction in streaming LLMs by learning semantic sufficiency cues from partial inputs through mask-based modeling and synchronized privileged self-distillation without external supervision.
-
EmbGen: Teaching with Reassembled Corpora
EmbGen creates synthetic QA data by entity decomposition, embedding-based reassembly into clusters, and multi-level sampling with cluster-specific prompts, yielding up to 88.9% higher Binary Accuracy than baselines on heterogeneous datasets under fixed token budgets.
-
A Multi-Agent Framework for Feature-Constrained Difficulty Control in Reading Comprehension Item Generation
MAFIG is a multi-agent framework that uses LLM agents and evaluators to generate reading comprehension items with significantly higher adherence to specified feature constraints than single-agent baselines.
-
ProxyKV: Cross-Model Proxy Pruning for Efficient Long-Context LLM Inference
ProxyKV offloads KV cache importance scoring to a lightweight intra-family small-model proxy with HybridAxialMapper and ranking-focused loss, matching KVZip accuracy while achieving up to 3.21x prefilling speedup on models up to 32B.
-
PragLocker: Protecting Agent Intellectual Property in Untrusted Deployments via Non-Portable Prompts
PragLocker generates function-preserving but non-portable prompts for LLM agents via code-symbol semantic anchoring followed by target-model feedback noise injection.
-
Effective Performance Measurement: Challenges and Opportunities in KPI Extraction from Earnings Calls
Encoder models trained on SEC filings struggle with earnings calls due to domain shift, while LLMs enable open-ended KPI extraction with 79.7% human-verified precision on newly introduced benchmarks.
-
The Override Gap: A Magnitude Account of Knowledge Conflict Failure in Hypernetwork-Based Instant LLM Adaptation
Knowledge conflicts in hypernetwork LLM adaptation stem from constant adapter margins losing to frequency-dependent pretrained margins; selective layer boosting and conflict-aware triggering raise deep-conflict accuracy to 71-72.5% on Gemma-2B and Mistral-7B.
-
Are Large Language Models Economically Viable for Industry Deployment?
Small LLMs under 2B parameters achieve better economic break-even, energy efficiency, and hardware density than larger models on legacy GPUs for industrial tasks.
-
HiGMem: A Hierarchical and LLM-Guided Memory System for Long-Term Conversational Agents
HiGMem combines hierarchical event-turn memory with LLM-guided selection to retrieve concise relevant evidence from long dialogues, improving F1 scores and cutting retrieved turns by an order of magnitude on the LoCoMo10 benchmark.
-
Transforming External Knowledge into Triplets for Enhanced Retrieval in RAG of LLMs
Tri-RAG turns external knowledge into Condition-Proof-Conclusion triplets and retrieves via the Condition anchor to improve efficiency and quality in LLM RAG.
-
Memory-Efficient Transfer Learning with Fading Side Networks via Masked Dual Path Distillation
MDPD mutually distills knowledge between a frozen backbone and a learnable side network during fine-tuning, then discards the side network at inference to accelerate speed by at least 25% while preserving accuracy.
-
MP-ISMoE: Mixed-Precision Interactive Side Mixture-of-Experts for Efficient Transfer Learning
MP-ISMoE uses Gaussian noise perturbed iterative quantization and interactive side mixture-of-experts to deliver higher accuracy than prior memory-efficient transfer learning methods while keeping similar parameter and memory usage.
-
Watt Counts: Energy-Aware Benchmark for Sustainable LLM Inference on Heterogeneous GPU Architectures
Watt Counts supplies over 5,000 energy measurements across 50 LLMs and 10 GPUs and shows that hardware-aware selection can reduce server-scenario energy use by up to 70 percent with little effect on user experience.
-
GCoT-Decoding: Unlocking Deep Reasoning Paths for Universal Question Answering
GCoT-decoding combines Fibonacci sampling, heuristic backtracking, span-based confidence scoring, and semantic consensus aggregation to enable general chain-of-thought reasoning without task-specific prompts.
-
JU\'A -- A Benchmark for Information Retrieval in Brazilian Legal Text Collections
JU'A is a new heterogeneous benchmark for Brazilian legal IR that distinguishes retrieval methods and shows domain-adapted models excel on aligned subsets while BM25 stays competitive elsewhere.
-
Can We Trust a Black-box LLM? LLM Untrustworthy Boundary Detection via Bias-Diffusion and Multi-Agent Reinforcement Learning
GMRL-BD detects untrustworthy topic boundaries for black-box LLMs by combining bias-diffusion on a Wikipedia KG with multi-agent RL, supported by a released dataset labeling biases in models like Llama2 and Qwen2.
-
Beyond Content Safety: Real-Time Monitoring for Reasoning Vulnerabilities in Large Language Models
An external zero-shot monitor detects nine unsafe reasoning behaviors in LLMs at 87% step-level accuracy with low false positives and low latency.
-
Chain-of-Authorization: Embedding authorization into large language models
LLMs fine-tuned to output authorization trajectories as a prerequisite for responses achieve high rejection rates for unauthorized prompts while preserving utility in allowed scenarios.
-
AGZO: Activation-Guided Zeroth-Order Optimization for LLM Fine-Tuning
AGZO restricts ZO perturbations to an activation-derived low-rank subspace, claiming higher gradient cosine similarity and better benchmark performance than isotropic ZO baselines on Qwen3 and Pangu models.
-
Progress Ratio Embeddings: An Impatience Signal for Robust Length Control in Neural Text Generation
Progress Ratio Embeddings use a trigonometric progress-ratio signal to deliver stable length control in transformers that generalizes to unseen target lengths.
-
You Had One Job: Per-Task Quantization Using LLMs' Hidden Representations
TAQ estimates per-layer importance from hidden representations and output sensitivity on task calibration data to allocate mixed precision in a training-free PTQ setting, outperforming task-agnostic baselines on accuracy-memory ratio across benchmarks.
-
HyperAdapt: Simple High-Rank Adaptation
HyperAdapt performs parameter-efficient fine-tuning by row- and column-wise diagonal scaling to induce high-rank updates with only n+m trainable parameters.
-
PromptSuite: A Task-Agnostic Framework for Multi-Prompt Generation
PromptSuite is a modular, extensible, task-agnostic framework for automatically generating diverse prompt variations to support robust multi-prompt LLM evaluation.
-
MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agent
MemAgent uses multi-conversation RL to train a memory agent that reads text in segments and overwrites memory, extrapolating from 8K training to 3.5M token QA with under 5% loss and 95%+ on 512K RULER.
-
RoboEval: Where Robotic Manipulation Meets Structured and Scalable Evaluation
RoboEval is a new benchmark providing eight bimanual tasks, thousands of expert demonstrations, and standardized metrics for efficiency, coordination, safety, and failure localization in robotic manipulation.
-
Online Conformal Abstention for Factuality Control Under Adversarial Bandit Feedback
ExAUL converts any bandit algorithm's regret into an O(sqrt(T)) FDR bound for online conformal abstention under partial adversarial feedback via a conversion lemma and feedback unlocking.
-
NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models
NV-Embed achieves first place on the MTEB leaderboard across 56 tasks by combining a latent attention layer, causal-mask removal, two-stage contrastive training, and data curation for LLM-based embedding models.
-
Defending Against Indirect Prompt Injection Attacks With Spotlighting
Spotlighting prompt transformations cut indirect prompt injection success rates from >50% to <2% on GPT models while preserving task performance.
-
Nomic Embed: Training a Reproducible Long Context Text Embedder
Nomic AI produced and open-sourced a reproducible 8192-context English text embedder that exceeds OpenAI Ada-002 and text-embedding-3-small performance on MTEB short-context and LoCo long-context benchmarks.
-
The Falcon Series of Open Language Models
Falcon-180B is a 180B-parameter open decoder-only model trained on 3.5 trillion tokens that approaches PaLM-2-Large performance at lower cost and is released with dataset extracts.
-
DeepSpeed Ulysses: System Optimizations for Enabling Training of Extreme Long Sequence Transformer Models
DeepSpeed-Ulysses keeps communication volume constant for sequence-parallel attention when sequence length and device count scale together, delivering 2.5x faster training on 4x longer sequences than prior SOTA.