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
Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks
16 Pith papers cite this work. Polarity classification is still indexing.
16
Pith papers citing it
hub tools
citation-role summary
method 2
citation-polarity summary
roles
method 2polarities
use method 2representative citing papers
Adaptive Instruction Composition uses a neural contextual bandit with RL to adaptively combine crowdsourced texts, generating more effective and diverse LLM jailbreaks than random or prior adaptive methods on Harmbench.
RouterBench supplies a standardized benchmark, 405k+ inference dataset, theoretical framework, and comparative analysis for multi-LLM routing systems.
MultiHop-RAG is a new benchmark dataset demonstrating that existing retrieval-augmented generation systems perform poorly on multi-hop queries requiring retrieval and reasoning over multiple evidence pieces.
Perfect permutation recovery under unknown scalar affine transformation is achievable when the minimal separation distance scales as sqrt(rho_sigma) vee (d log n)^{1/4} vee sqrt(log n).
PPAT residualizes losses via a prediction-powered control variate inside LURE, yielding lower-variance unbiased risk estimates, tailored acquisition, and asymptotic CIs that cover with fewer labels.
Nexa learns a response-conditioned policy that starts with parallel agent execution and adds at most one round of sequential message passing via a predicted sparse DAG, strictly subsuming pure parallel mode.
ProCompNav builds a candidate pool from ambiguous queries then uses pool-splitting binary questions for disambiguation, improving success rate and shortening responses on CoIN-Bench and TextNav.
GEM achieves 65.19% joint goal accuracy on MultiWOZ 2.2 by routing between a graph neural network expert for dialogue structure and a T5 expert for sequences, plus ReAct agents for value generation, outperforming prior SOTA methods.
COMPASS uses semantic clustering on multilingual embeddings to select auxiliary data for PEFT adapters, outperforming linguistic-similarity baselines on multilingual benchmarks while supporting continual adaptation.
REGLU guides LoRA-based unlearning via representation subspaces and orthogonal regularization to outperform prior methods on forget-retain trade-off in LLM benchmarks.
TF-IDF identifies labeled experts in the top 25 recommendations 79.5% of the time versus 51.5% for GPT-4o mini on an astronomy observatory dataset.
PROPARAG uses LLMs to assess real-world policies against 1,007 NIST controls, reaching F1 scores of 88.54 and 82.31 while identifying gaps and generating recommendations.
DoRA generates synthetic RAG training and evaluation data from 40 defense documents, halving hallucination rates in a LoRA-adapted Llama3.1-8B compared to 8 baselines.
ModernBERT is a new bidirectional encoder model achieving SOTA performance on diverse classification and retrieval benchmarks while offering superior speed and memory efficiency for long-context inference.
Shapley values for LLM explanations in financial text are shown via theory and experiments to produce attributions consistent with financial reasoning.
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.
-
Adaptive Instruction Composition for Automated LLM Red-Teaming
Adaptive Instruction Composition uses a neural contextual bandit with RL to adaptively combine crowdsourced texts, generating more effective and diverse LLM jailbreaks than random or prior adaptive methods on Harmbench.
-
RouterBench: A Benchmark for Multi-LLM Routing System
RouterBench supplies a standardized benchmark, 405k+ inference dataset, theoretical framework, and comparative analysis for multi-LLM routing systems.
-
MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries
MultiHop-RAG is a new benchmark dataset demonstrating that existing retrieval-augmented generation systems perform poorly on multi-hop queries requiring retrieval and reasoning over multiple evidence pieces.
-
Exact Permutation Recovery Under Unknown Scalar Affine Transformation
Perfect permutation recovery under unknown scalar affine transformation is achievable when the minimal separation distance scales as sqrt(rho_sigma) vee (d log n)^{1/4} vee sqrt(log n).
-
Prediction-Powered Active Testing
PPAT residualizes losses via a prediction-powered control variate inside LURE, yielding lower-variance unbiased risk estimates, tailored acquisition, and asymptotic CIs that cover with fewer labels.
-
Response-Conditioned Parallel-to-Sequential Orchestration for Multi-Agent Systems
Nexa learns a response-conditioned policy that starts with parallel agent execution and adds at most one round of sequential message passing via a predicted sparse DAG, strictly subsuming pure parallel mode.
-
ProCompNav: Proactive Instance Navigation with Comparative Judgment for Ambiguous User Queries
ProCompNav builds a candidate pool from ambiguous queries then uses pool-splitting binary questions for disambiguation, improving success rate and shortening responses on CoIN-Bench and TextNav.
-
GEM: Graph-Enhanced Mixture-of-Experts with ReAct Agents for Dialogue State Tracking
GEM achieves 65.19% joint goal accuracy on MultiWOZ 2.2 by routing between a graph neural network expert for dialogue structure and a T5 expert for sequences, plus ReAct agents for value generation, outperforming prior SOTA methods.
-
COMPASS: COntinual Multilingual PEFT with Adaptive Semantic Sampling
COMPASS uses semantic clustering on multilingual embeddings to select auxiliary data for PEFT adapters, outperforming linguistic-similarity baselines on multilingual benchmarks while supporting continual adaptation.
-
Representation-Guided Parameter-Efficient LLM Unlearning
REGLU guides LoRA-based unlearning via representation subspaces and orthogonal regularization to outperform prior methods on forget-retain trade-off in LLM benchmarks.
-
Traditional statistical representations outperform generative AI in identifying expert peer reviewers
TF-IDF identifies labeled experts in the top 25 recommendations 79.5% of the time versus 51.5% for GPT-4o mini on an astronomy observatory dataset.
-
An Automated Framework for Cybersecurity Policy Compliance Assessment Against Security Control Standards
PROPARAG uses LLMs to assess real-world policies against 1,007 NIST controls, reaching F1 scores of 88.54 and 82.31 while identifying gaps and generating recommendations.
-
A Benchmark Construction and Evaluation Framework for Specialist Domains: Case Study on Defense-related Documents
DoRA generates synthetic RAG training and evaluation data from 40 defense documents, halving hallucination rates in a LoRA-adapted Llama3.1-8B compared to 8 baselines.
-
Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference
ModernBERT is a new bidirectional encoder model achieving SOTA performance on diverse classification and retrieval benchmarks while offering superior speed and memory efficiency for long-context inference.
-
Shapley in Context: Explaining Financial Language with Domain Expertise
Shapley values for LLM explanations in financial text are shown via theory and experiments to produce attributions consistent with financial reasoning.