A fitted iso-depth scaling law measures that one recurrence in looped transformers is worth r^0.46 unique blocks in validation loss.
hub
TLDR9+: A large scale resource for extreme summarization of social media posts
12 Pith papers cite this work. Polarity classification is still indexing.
12
Pith papers citing it
hub tools
representative citing papers
NL2SQLBench is a new modular benchmarking framework that evaluates LLM NL2SQL methods across three core modules on existing datasets, exposing large accuracy gaps and computational inefficiency.
DPUA is a two-phase framework that aligns LLM uncertainty expressions with human disagreement distributions in subjectivity analysis while preserving task performance.
LLMs exhibit pseudo-deliberation, with consistent value-action misalignment in generated dialogues despite reasoning, as measured by the new VALDI framework across 4941 scenarios.
Latent-GRPO stabilizes reinforcement learning in latent space, delivering 7.86 Pass@1 gains on low-difficulty tasks over latent baselines and 4.27 points over explicit GRPO on high-difficulty tasks with 3-4x shorter reasoning chains.
LCF detects multiple LLM runtime threats by computing aggregated diagonal Mahalanobis distances on layer-wise hidden-state differences, calibrated on clean examples, achieving high detection rates with low overhead across several model architectures.
A context-aware Sentinel-Strategist system for RAG selectively applies defenses to block membership inference and data poisoning while recovering most retrieval utility compared to always-on defense stacks.
Token-level contrastive attribution yields informative signals for some LLM benchmark failures but is not universally applicable across datasets and models.
Sparrow uses targeted rule-based human feedback and evidence provision to outperform baselines in preference while violating rules only 8% of the time under adversarial probing.
Re-evaluating controlled text generation systems under standardized conditions reveals that many published performance claims do not hold, highlighting the need for consistent evaluation practices.
CEZSAR uses contrastive learning to align video and sentence embeddings with automatic negative sampling, claiming state-of-the-art zero-shot action recognition on UCF-101 and Kinetics-400.
Latent reasoning models often ignore their latent tokens for predictions and their correct outputs can be decoded into natural language reasoning traces more reliably than incorrect outputs.
citing papers explorer
-
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.
-
NL2SQLBench: A Modular Benchmarking Framework for LLM-Enabled NL2SQL Solutions
NL2SQLBench is a new modular benchmarking framework that evaluates LLM NL2SQL methods across three core modules on existing datasets, exposing large accuracy gaps and computational inefficiency.
-
Aligning LLM Uncertainty with Human Disagreement in Subjectivity Analysis
DPUA is a two-phase framework that aligns LLM uncertainty expressions with human disagreement distributions in subjectivity analysis while preserving task performance.
-
Pseudo-Deliberation in Language Models: When Reasoning Fails to Align Values and Actions
LLMs exhibit pseudo-deliberation, with consistent value-action misalignment in generated dialogues despite reasoning, as measured by the new VALDI framework across 4941 scenarios.
-
Latent-GRPO: Group Relative Policy Optimization for Latent Reasoning
Latent-GRPO stabilizes reinforcement learning in latent space, delivering 7.86 Pass@1 gains on low-difficulty tasks over latent baselines and 4.27 points over explicit GRPO on high-difficulty tasks with 3-4x shorter reasoning chains.
-
Layerwise Convergence Fingerprints for Runtime Misbehavior Detection in Large Language Models
LCF detects multiple LLM runtime threats by computing aggregated diagonal Mahalanobis distances on layer-wise hidden-state differences, calibrated on clean examples, achieving high detection rates with low overhead across several model architectures.
-
Adaptive Defense Orchestration for RAG: A Sentinel-Strategist Architecture against Multi-Vector Attacks
A context-aware Sentinel-Strategist system for RAG selectively applies defenses to block membership inference and data poisoning while recovering most retrieval utility compared to always-on defense stacks.
-
Contrastive Attribution in the Wild: An Interpretability Analysis of LLM Failures on Realistic Benchmarks
Token-level contrastive attribution yields informative signals for some LLM benchmark failures but is not universally applicable across datasets and models.
-
Improving alignment of dialogue agents via targeted human judgements
Sparrow uses targeted rule-based human feedback and evidence provision to outperform baselines in preference while violating rules only 8% of the time under adversarial probing.
-
A Comparative Study of Controlled Text Generation Systems Using Level-Playing-Field Evaluation Principles
Re-evaluating controlled text generation systems under standardized conditions reveals that many published performance claims do not hold, highlighting the need for consistent evaluation practices.
-
CEZSAR: A Contrastive Embedding Method for Zero-Shot Action Recognition
CEZSAR uses contrastive learning to align video and sentence embeddings with automatic negative sampling, claiming state-of-the-art zero-shot action recognition on UCF-101 and Kinetics-400.
-
Are Latent Reasoning Models Easily Interpretable?
Latent reasoning models often ignore their latent tokens for predictions and their correct outputs can be decoded into natural language reasoning traces more reliably than incorrect outputs.