相关论文: LIME-LLM: Probing Models with Fluent Counterfactua…

Large Language Models (LLMs) are transforming scientific hypothesis generation and validation by enabling information synthesis, latent relationship discovery, and reasoning augmentation. This survey provides a structured overview of…

This paper provides an in-depth examination of the concept of semantic diffusion as a complementary instrument to large language models (LLMs) for design applications. Conventional LLMs and diffusion models fail to induce a convergent,…

Hallucination in large language models (LLMs) can be detected by assessing the uncertainty of model outputs, typically measured using entropy. Semantic entropy (SE) enhances traditional entropy estimation by quantifying uncertainty at the…

Large Language Models (LLMs) exhibit emerging in-context learning abilities through prompt engineering. The recent progress in large-scale generative models has further expanded their use in real-world language applications. However, the…

In this paper we propose a new framework for evaluating the performance of explanation methods on the decisions of a deepfake detector. This framework assesses the ability of an explanation method to spot the regions of a fake image with…

Current methods for Black-Box NLP interpretability, like LIME or SHAP, are based on altering the text to interpret by removing words and modeling the Black-Box response. In this paper, we outline limitations of this approach when using…

Large pretrained language models are critical components of modern NLP pipelines. Yet, they suffer from spurious correlations, poor out-of-domain generalization, and biases. Inspired by recent progress in causal machine learning, in…

Recent advances in large language models (LLMs) have yielded impressive performance on various tasks, yet they often depend on high-quality feedback that can be costly. Self-refinement methods attempt to leverage LLMs' internal evaluation…

Large language model (LLM) question-answering systems often fail on community-specific queries, creating "knowledge blind spots" that marginalize local voices and reinforce epistemic injustice. We present Collective Narrative Grounding, a…

While Large Language Models (LLMs) have achieved strong performance across many NLP tasks, their opaque internal mechanisms hinder trustworthiness and safe deployment. Existing surveys in explainable AI largely focus on post-hoc explanation…

As Large Language Models (LLMs) become increasingly integrated into many technological ecosystems across various domains and industries, identifying which model is deployed or being interacted with is critical for the security and…

We present REMARK-LLM, a novel efficient, and robust watermarking framework designed for texts generated by large language models (LLMs). Synthesizing human-like content using LLMs necessitates vast computational resources and extensive…

Rule-based reasoning over natural language input arises in domains where decisions must be auditable and justifiable: clinical protocols specify eligibility criteria in prose, evidence rules define admissibility through textual conditions,…

Diffusion Large Language Models (dLLMs) have demonstrated promising generative capabilities and are increasingly used to produce formal languages defined by context-free grammars, such as source code and chemical expressions. However, as…

Causal explanations of the predictions of NLP systems are essential to ensure safety and establish trust. Yet, existing methods often fall short of explaining model predictions effectively or efficiently and are often model-specific. In…

As large language models (LLMs) become integrated into everyday and high-stakes decision-making, they inherit the ambiguity and biases of human language. While they produce fluent and coherent outputs, they rely on statistical pattern…

We propose WHISPER-GPT: A generative large language model (LLM) for speech and music that allows us to work with continuous audio representations and discrete tokens simultaneously as part of a single architecture. There has been a huge…

In this work, we instantiate a novel perturbation-based multi-class explanation framework, LIPEx (Locally Interpretable Probabilistic Explanation). We demonstrate that LIPEx not only locally replicates the probability distributions output…

The zero-shot capability of Large Language Models (LLMs) has enabled highly flexible, reference-free metrics for various tasks, making LLM evaluators common tools in NLP. However, the robustness of these LLM evaluators remains relatively…

In this paper, we propose Precision-Informed Semantic Modeling (PRISM), a structured topic modeling framework combining the benefits of rich representations captured by LLMs with the low cost and interpretability of latent semantic…