A stop-gradient consistency regularizer mitigates context-induced degradation in on-policy distillation, improving robustness across 12 configurations.
T weet E val: Unified Benchmark and Comparative Evaluation for Tweet Classification
11 Pith papers cite this work. Polarity classification is still indexing.
11
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
Pruning attention layers in five LLMs across eight datasets maintains accuracy but degrades faithfulness and calibration.
LLMs recover dominant binomial orders from corpora but align less closely with exact preference distributions, with preference strength partially encoded in middle-to-late layers and manipulable via steering.
Conceptors as soft projection matrices from bipolar activations offer a multidimensional, compositional, and geometrically principled method for semantic steering in LLMs that outperforms single-vector baselines in multi-dimensional subspaces.
Introduces the LLM ORDER BY semantic operator with algorithmic improvements, a semantic-aware external merge sort, and a budget-aware optimizer that selects near-optimal access paths for LLM-based ordering.
UltraChat supplies 1.5 million high-quality multi-turn dialogues that, when used to fine-tune LLaMA, produce UltraLLaMA, which outperforms prior open-source chat models including Vicuna.
Introduces the first interpersonal emotion dataset from congressional tweets and demonstrates that joint neural modeling of interpersonal group relationships and emotions yields performance gains on both.
LLMs show minimal sociodemographic disparities in advice because they infer user demographics poorly from history; conversation topics are the main predictor and act as proxies for groups.
LLMs achieve Pearson correlations up to 0.97 and 94% classification accuracy on product desirability sentiment from qualitative data, outperforming lexicon and transformer baselines while providing confidence ratings and rationales.
A modular XR platform integrates Whisper, NLLB, AWS Polly, RoBERTa, flan-t5, and MediaPipe to deliver real-time multilingual and International Sign support for education, with benchmarks showing AWS Polly's low latency and EuroLLM's higher BLEU score.
citing papers explorer
-
Access Paths for Efficient Ordering with Large Language Models
Introduces the LLM ORDER BY semantic operator with algorithmic improvements, a semantic-aware external merge sort, and a budget-aware optimizer that selects near-optimal access paths for LLM-based ordering.