InsightGen uses thematic clustering and graph neighborhood selection to generate diverse, relevant insights for open-ended document-grounded questions and releases the SCOpE-QA dataset of 3000 questions.
hub
In: Gurevych, I., Miyao, Y
29 Pith papers cite this work, alongside 2,164 external citations. Polarity classification is still indexing.
29
Pith papers citing it
2,164
external citations · OpenAlex
hub tools
citation-role summary
background 1
dataset 1
citation-polarity summary
representative citing papers
UrduMMLU is a new native-source MCQ benchmark for Urdu that reveals top LLMs reach only ~90% accuracy with large gaps on region-specific humanities content.
SuperMemory-VQA provides 4,853 human-verified QA pairs from 52.9 hours of egocentric AI glasses recordings to benchmark AI systems on realistic long-horizon memory tasks including an unanswerable option.
A fitted iso-depth scaling law measures that one recurrence in looped transformers is worth r^0.46 unique blocks in validation loss.
Preconditioned delta-rule models with a diagonal curvature approximation improve upon standard DeltaNet, GDN, and KDA by better approximating the test-time regression objective.
Task prompt vectors, formed by subtracting random initialization from tuned soft prompts, support low-resource initialization and arithmetic combination across tasks on 12 NLU datasets while remaining independent of initialization seed on two model architectures.
ALBERT reduces BERT parameters via embedding factorization and layer sharing, adds inter-sentence coherence pretraining, and reaches SOTA on GLUE, RACE, and SQuAD with fewer parameters than BERT-large.
AURORA detects hallucinations via skewness of cosine similarities between weights and gradients plus a rotation ratio from SVD on update-induced changes to singular vectors.
ARIADNE routes queries to the best adapter via embedding-space centroid proximity, recovering 97.44% of upper-bound performance on 23 NLP tasks and 89.7% selection accuracy on 44 tasks without training or internal access.
TriLens detects hallucinations via per-layer entropy trajectories of logit-lens readouts from three internal modules across LLMs and QA benchmarks.
MVR-cache raises semantic cache hit rates by up to 37% on benchmarks using learned prompt segmentation, multi-vector retrieval, and RL training while preserving correctness.
SANTA replaces full value-cache multiply-accumulates with stochastic gather-and-add sampling from the attention distribution to reduce memory bandwidth while preserving an unbiased estimator.
Architecture and training determine whether transformers retain a readable internal signal that lets activation monitors catch errors missed by output confidence.
A hybrid graph-text retrieval system for cyber threat intelligence improves multi-hop question answering by up to 35% over vector-based RAG on a 3,300-question benchmark.
A human-centered design workshop with journalism practitioners yields an evaluation cookbook and design requirements for contextualized, value-aligned generative AI benchmarks.
Controlled ablations of 38 models find MLM superior to CLM on representation benchmarks while CLM offers better data efficiency and stability; a biphasic CLM-then-MLM schedule is optimal under fixed compute and improves when initialized from pretrained CLM models.
Gated linear attention Transformers achieve competitive language modeling results with linear-time inference, superior length generalization, and higher training throughput than Mamba.
AdaLoRA uses SVD-based pruning to allocate the parameter budget for low-rank fine-tuning updates according to per-matrix importance scores, yielding better performance than uniform allocation especially under tight budgets.
Q-Delta extends linear attention by introducing a query-conditioned delta rule that incorporates mixed key-query errors into recurrent state updates for improved stability and performance.
Introduces LLM-FACETS, a privacy-preserving open-source framework for LLM evaluation using deterministic metrics locally, LLM-judge metrics with user-controlled APIs, and mechanisms for uncertainty visualization and hallucination detection.
JTS trains reasoning models via supervised warm-up and missing-premise RL to make an explicit answerability commitment that triggers early termination on unanswerable inputs, raising Abstention@Detection near saturation.
By restricting token mixing to rank-1 decayed matrices, the same model trains in parallel but generates recurrently with constant memory, yielding large throughput gains in compute-matched benchmarks.
Toeplitz MLP Mixers replace attention with masked Toeplitz multiplications for sub-quadratic complexity while retaining more sequence information and outperforming on copying and in-context tasks.
Gated DeltaNet integrates gating and delta rules into linear transformers, outperforming Mamba2 and DeltaNet on language modeling, reasoning, retrieval, and long-context tasks.
citing papers explorer
-
An Answer is just the Start: Related Insight Generation for Open-Ended Document-Grounded QA
InsightGen uses thematic clustering and graph neighborhood selection to generate diverse, relevant insights for open-ended document-grounded questions and releases the SCOpE-QA dataset of 3000 questions.
-
UrduMMLU: A Massive Multitask Benchmark for Urdu Language Understanding
UrduMMLU is a new native-source MCQ benchmark for Urdu that reveals top LLMs reach only ~90% accuracy with large gaps on region-specific humanities content.
-
SuperMemory-VQA: An Egocentric Visual Question-Answering Benchmark for Long-Horizon Memory
SuperMemory-VQA provides 4,853 human-verified QA pairs from 52.9 hours of egocentric AI glasses recordings to benchmark AI systems on realistic long-horizon memory tasks including an unanswerable option.
-
How Much Is One Recurrence Worth? Iso-Depth Scaling Laws for Looped Language Models
A fitted iso-depth scaling law measures that one recurrence in looped transformers is worth r^0.46 unique blocks in validation loss.
-
Preconditioned DeltaNet: Curvature-aware Sequence Modeling for Linear Recurrences
Preconditioned delta-rule models with a diagonal curvature approximation improve upon standard DeltaNet, GDN, and KDA by better approximating the test-time regression objective.
-
Task Prompt Vectors: Effective Initialization through Multi-Task Soft-Prompt Transfer
Task prompt vectors, formed by subtracting random initialization from tuned soft prompts, support low-resource initialization and arithmetic combination across tasks on 12 NLU datasets while remaining independent of initialization seed on two model architectures.
-
ALBERT: A Lite BERT for Self-supervised Learning of Language Representations
ALBERT reduces BERT parameters via embedding factorization and layer sharing, adds inter-sentence coherence pretraining, and reaches SOTA on GLUE, RACE, and SQuAD with fewer parameters than BERT-large.
-
AURORA: Asymmetry and Update-Induced Rotation for Robust Hallucination Detection in Large Language Models
AURORA detects hallucinations via skewness of cosine similarities between weights and gradients plus a rotation ratio from SVD on update-induced changes to singular vectors.
-
ARIADNE: Agnostic Routing for Inference-time Adapter DyNamic sElection
ARIADNE routes queries to the best adapter via embedding-space centroid proximity, recovering 97.44% of upper-bound performance on 23 NLP tasks and 89.7% selection accuracy on 44 tasks without training or internal access.
-
TriLens: Per-Layer Logit-Lens Entropy for White-Box Hallucination Detection
TriLens detects hallucinations via per-layer entropy trajectories of logit-lens readouts from three internal modules across LLMs and QA benchmarks.
-
MVR-cache: Optimizing Semantic Caching via Multi-Vector Retrieval and Learned Prompt Segmentation
MVR-cache raises semantic cache hit rates by up to 37% on benchmarks using learned prompt segmentation, multi-vector retrieval, and RL training while preserving correctness.
-
Stochastic Sparse Attention for Memory-Bound Inference
SANTA replaces full value-cache multiply-accumulates with stochastic gather-and-add sampling from the attention distribution to reduce memory bandwidth while preserving an unbiased estimator.
-
Architecture Determines Observability of Transformers
Architecture and training determine whether transformers retain a readable internal signal that lets activation monitors catch errors missed by output confidence.
-
Beyond RAG for Cyber Threat Intelligence: A Systematic Evaluation of Graph-Based and Agentic Retrieval
A hybrid graph-text retrieval system for cyber threat intelligence improves multi-hop question answering by up to 35% over vector-based RAG on a 3,300-question benchmark.
-
Towards Real-World Validity in Generative AI Benchmarks: Understanding and Designing Domain-Centered Evaluations for Journalism Practitioners
A human-centered design workshop with journalism practitioners yields an evaluation cookbook and design requirements for contextualized, value-aligned generative AI benchmarks.
-
Should We Still Pretrain Encoders with Masked Language Modeling?
Controlled ablations of 38 models find MLM superior to CLM on representation benchmarks while CLM offers better data efficiency and stability; a biphasic CLM-then-MLM schedule is optimal under fixed compute and improves when initialized from pretrained CLM models.
-
Gated Linear Attention Transformers with Hardware-Efficient Training
Gated linear attention Transformers achieve competitive language modeling results with linear-time inference, superior length generalization, and higher training throughput than Mamba.
-
AdaLoRA: Adaptive Budget Allocation for Parameter-Efficient Fine-Tuning
AdaLoRA uses SVD-based pruning to allocate the parameter budget for low-rank fine-tuning updates according to per-matrix importance scores, yielding better performance than uniform allocation especially under tight budgets.
-
Q-Delta: Beyond Key-Value Associative State Evolution
Q-Delta extends linear attention by introducing a query-conditioned delta rule that incorporates mixed key-query errors into recurrent state updates for improved stability and performance.
-
LLM-FACETS: A Privacy-Preserving Framework for Evaluating LLM Transparency and Accountability
Introduces LLM-FACETS, a privacy-preserving open-source framework for LLM evaluation using deterministic metrics locally, LLM-judge metrics with user-controlled APIs, and mechanisms for uncertainty visualization and hallucination detection.
-
Bridging the Detection-to-Abstention Gap in Reasoning Models under Insufficient Information
JTS trains reasoning models via supervised warm-up and missing-premise RL to make an explicit answerability commitment that triggers early termination on unanswerable inputs, raising Abstention@Detection near saturation.
-
Structured Recurrent Mixers for Massively Parallelized Sequence Generation
By restricting token mixing to rank-1 decayed matrices, the same model trains in parallel but generates recurrently with constant memory, yielding large throughput gains in compute-matched benchmarks.
-
Toeplitz MLP Mixers are Low Complexity, Information-Rich Sequence Models
Toeplitz MLP Mixers replace attention with masked Toeplitz multiplications for sub-quadratic complexity while retaining more sequence information and outperforming on copying and in-context tasks.
-
Gated Delta Networks: Improving Mamba2 with Delta Rule
Gated DeltaNet integrates gating and delta rules into linear transformers, outperforming Mamba2 and DeltaNet on language modeling, reasoning, retrieval, and long-context tasks.
-
PaLM 2 Technical Report
PaLM 2 reports state-of-the-art results on language, reasoning, and multilingual tasks with improved efficiency over PaLM.
-
Ling and Ring 2.6 Technical Report: Efficient and Instant Agentic Intelligence at Trillion-Parameter Scale
Technical report announcing Ling-2.6 and Ring-2.6 models with hybrid linear attention, evolutionary CoT, and KPop RL for efficient agentic intelligence at scale.
-
The Master-Slave Encoder Model for Improving Patent Text Summarization: A New Approach to Combining Specifications and Claims
MSEA uses a master-slave encoder architecture on patent specifications and claims, enhanced with pointer networks and repetition suppression, to generate better summaries as measured by small ROUGE score gains.
-
A Tree-of-Thoughts Inspired Hybrid Approach for Legal Case Judgement Summarization using LLMs
A tree-of-thoughts inspired hybrid extractive-abstractive LLM prompt yields better legal case judgment summaries than standard extractive or abstractive prompts.
-
Qwen Goes Brrr: Off-the-Shelf RAG for Ukrainian Multi-Domain Document Understanding
A RAG pipeline with contextual PDF chunking, question-and-answer-aware retrieval and reranking using Qwen3 models reaches 0.96 accuracy on a Ukrainian multi-domain document QA shared task.