Natural Language Processing

This study presents a novel Inverse Reinforcement Learning (IRL) approach for fine-tuning large language models, offering improved performance and generation diversity compared to standard methods.

VLScore: a novel image-aware metric revolutionizes medical report evaluation by jointly assessing textual and visual similarities, significantly improving alignment with radiologist assessments.

IF-Font: Revolutionary font generation using Ideographic Description Sequences (IDS) to surpass state-of-the-art methods in style transfer, especially for unique styles.

IDGen synthesizes LLM evaluation prompts using Item Discrimination theory, creating a more challenging and discriminative dataset than previous methods.

I2EBench: a new benchmark for Instruction-based Image Editing provides a comprehensive evaluation framework using 16 dimensions, aligned with human perception, to evaluate IIE models objectively.

Boosting LLM accuracy, a new calibration method using a special [IDK] token explicitly models uncertainty, mitigating hallucinations, and improving factual precision while maintaining knowledge retent…

HYSYNTH: A hybrid approach uses LLMs to create context-free surrogate models that guide efficient program synthesis, outperforming LLMs alone and existing synthesizers across multiple domains.

HYDRA, a novel model factorization framework, significantly improves black-box LLM personalization by capturing both user-specific behavior and shared knowledge, achieving a 9.01% average relative imp…

Hydra: Bidirectional sequence modeling redefined with quasiseparable matrix mixers, outperforming existing models on various benchmarks!

HuRef: Generate unique, human-readable fingerprints for LLMs to protect copyright without exposing model parameters or impeding training.

Transformers struggle with complex reasoning tasks. This paper introduces ‘globality degree’ to measure task difficulty and shows that high globality hinders efficient learning. However, using ‘induc…

Pre-trained language models’ base capabilities are significantly influenced by architecture, not just scale; a novel Combination Enhanced Architecture (CEA) improves performance by addressing FFN-Wide…

LLMs surprisingly process multilingual queries via an English-centric intermediate stage before generating responses in the original language, a phenomenon explained by the proposed MWork framework an…

LLMs’ factual knowledge acquisition during pretraining is surprisingly non-linear: more data doesn’t guarantee better knowledge retention, and forgetting follows a power law.

HonestLLM boosts LLM honesty & helpfulness by 65.3% (Llama3-8b) and 124.7% (Mistral-7b) using training-free and fine-tuning methods, establishing principles and a new dataset (HONESET) for honesty eva…

HLM-Cite: A hybrid language model workflow boosts scientific citation prediction accuracy by 17.6% and scales to 100K candidate papers, surpassing existing methods.

HippoRAG, a neurobiologically inspired framework, dramatically improves LLM long-term memory and multi-hop question answering by synergistically orchestrating LLMs, knowledge graphs, and the Personali…

HENASY, a novel egocentric video-language model, uses a compositional approach to assemble scene entities for improved interpretability and performance.

HAWK: a novel framework leveraging interactive VLMs and motion modality achieves state-of-the-art performance in open-world video anomaly understanding, generating descriptions and answering questions…

GTBENCH reveals LLMs’ strategic reasoning weaknesses via game-theoretic evaluations, showing strengths in probabilistic scenarios but struggles with deterministic ones; code-pretraining helps.