LLMs are applied in a generative pipeline for extracting, normalizing, and interpreting eligibility criteria from securities prospectuses, achieving up to 91% precision in document-level decisions with a conservative bias.
Title resolution pending
12 Pith papers cite this work. Polarity classification is still indexing.
12
Pith papers citing it
citation-role summary
background 4
citation-polarity summary
verdicts
UNVERDICTED 12roles
background 4representative citing papers
HTEB introduces dynamic, multi-axis evaluation of text embedding robustness using LLM transformations, finding decoupled profiles across models and that scaling does not close all robustness gaps.
Full-sequence masking in SFT unlocks prompt infilling for masked diffusion language models, producing templates that match or surpass hand-designed ones and transfer across models.
Embedding model performance on MTEB tasks correlates strongly with nearest-neighbor overlap and ICA magnitude differences in their embedding spaces.
Vocabulary adaptation via targeted token addition and replacement improves semantic similarity, domain word usage, and training efficiency for LLM summarization in legal and medical domains.
A proposed pipeline shows LLMs introduce detectable race and gender biases when summarizing life narratives, creating potential for representational harm in research.
LLMs produce lower-fidelity summaries of identical public comments when attributed to lower-status occupations like street vendors versus financial analysts, with inconsistent race effects and no gender effects.
ConSUM reranks candidate summaries using MBR consensus and source-consistency metrics to improve factuality over standard generation or reranking baselines.
ATLAS is a length-dependent benchmarking framework that evaluates 26 models on 8 capability dimensions and shows substantial rank changes when moving from 128K to 1M token ranges.
The paper surveys hallucination in LLMs with an innovative taxonomy, factors, detection methods, benchmarks, mitigation strategies, and open research directions.
Audio language models are benchmarked on five semantic and paralinguistic reasoning tasks to reveal limitations in handling spoken audio evidence, accent variation, and domain shifts.
Fine-tuned multilingual LLMs achieve top shared-task scores on financial causality extraction in English and Spanish.
citing papers explorer
-
LLM-Based Examination of Eligibility Criteria from Securities Prospectuses at the German Central Bank
LLMs are applied in a generative pipeline for extracting, normalizing, and interpreting eligibility criteria from securities prospectuses, achieving up to 91% precision in document-level decisions with a conservative bias.
-
The Harder Text Embedding Benchmark (HTEB): Beyond One-dimensional Static Robustness
HTEB introduces dynamic, multi-axis evaluation of text embedding robustness using LLM transformations, finding decoupled profiles across models and that scaling does not close all robustness gaps.
-
Unlocking Prompt Infilling Capability for Diffusion Language Models
Full-sequence masking in SFT unlocks prompt infilling for masked diffusion language models, producing templates that match or surpass hand-designed ones and transfer across models.
-
Structure Retention in Embedding Spaces as a Predictor of Benchmark Performance
Embedding model performance on MTEB tasks correlates strongly with nearest-neighbor overlap and ICA magnitude differences in their embedding spaces.
-
Learning Faster with Better Tokens: Parameter-Efficient Vocabulary Adaptation for Specialized Text Summarization
Vocabulary adaptation via targeted token addition and replacement improves semantic similarity, domain word usage, and training efficiency for LLM summarization in legal and medical domains.
-
Whose Story Gets Told? Positionality and Bias in LLM Summaries of Life Narratives
A proposed pipeline shows LLMs introduce detectable race and gender biases when summarizing life narratives, creating potential for representational harm in research.
-
All Public Voices Are Equal, But Are Some More Equal Than Others to LLMs?
LLMs produce lower-fidelity summaries of identical public comments when attributed to lower-status occupations like street vendors versus financial analysts, with inconsistent race effects and no gender effects.
-
Enhancing Factuality through Consensus and Consistency in Summarization Using Minimum Bayes Risk Decoding
ConSUM reranks candidate summaries using MBR consensus and source-consistency metrics to improve factuality over standard generation or reranking baselines.
-
ATLAS: All-round Testing of Long-context Abilities across Scales
ATLAS is a length-dependent benchmarking framework that evaluates 26 models on 8 capability dimensions and shows substantial rank changes when moving from 128K to 1M token ranges.
-
A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions
The paper surveys hallucination in LLMs with an innovative taxonomy, factors, detection methods, benchmarks, mitigation strategies, and open research directions.
-
Afrispeech Semantics: Evaluating Audio Semantic Reasoning in Spoken Language Models Across Domains and Accents
Audio language models are benchmarked on five semantic and paralinguistic reasoning tasks to reveal limitations in handling spoken audio evidence, accent variation, and domain shifts.
-
Causal Connections: Leveraging Multilingual Fine-Tuning for Financial QA@FinCausal 2026
Fine-tuned multilingual LLMs achieve top shared-task scores on financial causality extraction in English and Spanish.