Develops a model-agnostic attribution score as the log-ratio of conditional response probabilities with and without a marginalized prompt token, derived via Bayes inversion of next-token distributions, and relates it to conditional entropies.
A Primer in BERT ology: What We Know About How BERT Works
11 Pith papers cite this work. Polarity classification is still indexing.
11
Pith papers citing it
verdicts
UNVERDICTED 11representative citing papers
RISE is an inference-time semantic reranking framework that refines low-confidence predictions in rhetorical role labeling using contrastively learned label representations, delivering an average +9.15 macro-F1 gain on hard examples across eight datasets and seven models.
LLMs achieve strong results on syntax parsing tasks but show limited and variable performance on dynamic reasoning, with a clear performance hierarchy across model scales.
Introduces predictive prefetching for RAG that anticipates retrieval needs several tokens ahead via three components, reporting up to 43.5% latency reduction and 62.4% TTFT improvement while preserving answer quality.
Larger LLMs reproduce constructional productivity via entrenchment in coercion cases with nonce words but fail to use statistical preemption to avoid overgeneralizing semantically plausible but unobserved patterns.
Training a mean-field Transformer under L2 regularization induces an escape from attention-driven token clustering in later layers after initial clustering.
Search-R3 trains LLMs to output search embeddings as a direct product of step-by-step reasoning via supervised pre-training and a specialized RL environment that avoids full corpus re-encoding.
Inflectional features stay linearly decodable across all layers while lexical identity weakens with depth in modern transformers.
EADP filters textual noise via statistical entropy then casts token selection as submodular maximization with spatial prior to preserve fine-grained cues in VLMs under strict budgets.
LRP-based attention head selection and distributed application improve the efficiency and accuracy of function vectors for steering LLMs compared to prior choices.
Probing classifiers are a common but limited method for analyzing linguistic knowledge in neural NLP models, and this review outlines their promises, methodological shortcomings, and recent advances.
citing papers explorer
-
Probabilistic Attribution For Large Language Models
Develops a model-agnostic attribution score as the log-ratio of conditional response probabilities with and without a marginalized prompt token, derived via Bayes inversion of next-token distributions, and relates it to conditional entropies.
-
Semantic Reranking at Inference Time for Hard Examples in Rhetorical Role Labeling
RISE is an inference-time semantic reranking framework that refines low-confidence predictions in rhetorical role labeling using contrastively learned label representations, delivering an average +9.15 macro-F1 gain on hard examples across eight datasets and seven models.
-
Exploring Code Analysis: Zero-Shot Insights on Syntax and Semantics with LLMs
LLMs achieve strong results on syntax parsing tasks but show limited and variable performance on dynamic reasoning, with a clear performance hierarchy across model scales.
-
Predictive Prefetching for Retrieval-Augmented Generation
Introduces predictive prefetching for RAG that anticipates retrieval needs several tokens ahead via three components, reporting up to 43.5% latency reduction and 62.4% TTFT improvement while preserving answer quality.
-
Linguistic Productivity in Large Language Models: Models Coerce, but do not Preempt
Larger LLMs reproduce constructional productivity via entrenchment in coercion cases with nonce words but fail to use statistical preemption to avoid overgeneralizing semantically plausible but unobserved patterns.
-
Training-Induced Escape from Token Clustering in a Mean-Field Formulation of Transformers
Training a mean-field Transformer under L2 regularization induces an escape from attention-driven token clustering in later layers after initial clustering.
-
Search-R3: Unifying Reasoning and Embedding in Large Language Models
Search-R3 trains LLMs to output search embeddings as a direct product of step-by-step reasoning via supervised pre-training and a specialized RL environment that avoids full corpus re-encoding.
-
Model Internal Sleuthing: Finding Lexical Identity and Inflectional Features in Modern Language Models
Inflectional features stay linearly decodable across all layers while lexical identity weakens with depth in modern transformers.
-
Combating Textual Noise and Redundancy: Entropy-Aware Dense Visual Token Pruning
EADP filters textual noise via statistical entropy then casts token selection as submodular maximization with spatial prior to preserve fine-grained cues in VLMs under strict budgets.
-
Fast & Faithful Function Vectors
LRP-based attention head selection and distributed application improve the efficiency and accuracy of function vectors for steering LLMs compared to prior choices.
-
Probing Classifiers: Promises, Shortcomings, and Advances
Probing classifiers are a common but limited method for analyzing linguistic knowledge in neural NLP models, and this review outlines their promises, methodological shortcomings, and recent advances.