Multi-Level Explanations for Generative Language Models

• URL: http://arxiv.org/abs/2403.14459v2
• Date: Wed, 23 Jul 2025 15:48:23 GMT
• Title: Multi-Level Explanations for Generative Language Models
• Authors: Lucas Monteiro Paes, Dennis Wei, Hyo Jin Do, Hendrik Strobelt, Ronny Luss, Amit Dhurandhar, Manish Nagireddy, Karthikeyan Natesan Ramamurthy, Prasanna Sattigeri, Werner Geyer, Soumya Ghosh,
• Abstract summary: We propose Multi-Level Explanations for Generative Language Models (MExGen)<n>MExGen assigns scores to parts of the context to quantify their influence on the model's output.<n>We conduct a systematic evaluation, both automated and human, of perturbation-based attribution methods for summarization and question answering.
• Score: 45.82956216020136
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Despite the increasing use of large language models (LLMs) for context-grounded tasks like summarization and question-answering, understanding what makes an LLM produce a certain response is challenging. We propose Multi-Level Explanations for Generative Language Models (MExGen), a technique to provide explanations for context-grounded text generation. MExGen assigns scores to parts of the context to quantify their influence on the model's output. It extends attribution methods like LIME and SHAP to LLMs used in context-grounded tasks where (1) inference cost is high, (2) input text is long, and (3) the output is text. We conduct a systematic evaluation, both automated and human, of perturbation-based attribution methods for summarization and question answering. The results show that our framework can provide more faithful explanations of generated output than available alternatives, including LLM self-explanations. We open-source code for MExGen as part of the ICX360 toolkit: https://github$.$com/IBM/ICX360.

Related papers

• On the Effectiveness of LLM-as-a-judge for Code Generation and Summarization [54.965787768076254]
  Large Language Models have been recently exploited as judges for complex natural language processing tasks, such as Q&A.<n>We study the effectiveness of LLMs-as-a-judge for two code-related tasks, namely code generation and code summarization.
  arXiv  Detail & Related papers  (2025-07-22T13:40:26Z)
• GEM: Empowering LLM for both Embedding Generation and Language Understanding [11.081595808236239]
  We propose Generative Embedding large language Model (GEM) to generate high-quality text embeddings.<n>Our method inserts new special token(s) into a text body, and generates summarization embedding of the text by manipulating the attention mask.<n>Our results indicate that our approach can empower LLMs with state-of-the-art text embedding capabilities while maintaining their original NLP performance.
  arXiv  Detail & Related papers  (2025-06-04T18:02:07Z)
• LAQuer: Localized Attribution Queries in Content-grounded Generation [69.60308443863606]
  Grounded text generation models often produce content that deviates from their source material, requiring user verification to ensure accuracy.<n>Existing attribution methods associate entire sentences with source documents, which can be overwhelming for users seeking to fact-check specific claims.<n>We introduce Localized Attribution Queries (LAQuer), a new task that localizes selected spans of generated output to their corresponding source spans, allowing fine-grained and user-directed attribution.
  arXiv  Detail & Related papers  (2025-06-01T21:46:23Z)
• New Dataset and Methods for Fine-Grained Compositional Referring Expression Comprehension via Specialist-MLLM Collaboration [49.180693704510006]
  Referring Expression (REC) is a cross-modal task that evaluates the interplay of language understanding, image comprehension, and language-to-image grounding.<n>It serves as an essential testing ground for Multimodal Large Language Models (MLLMs)
  arXiv  Detail & Related papers  (2025-02-27T13:58:44Z)
• Harnessing Large Language Models for Knowledge Graph Question Answering via Adaptive Multi-Aspect Retrieval-Augmentation [81.18701211912779]
  We introduce an Adaptive Multi-Aspect Retrieval-augmented over KGs (Amar) framework.<n>This method retrieves knowledge including entities, relations, and subgraphs, and converts each piece of retrieved text into prompt embeddings.<n>Our method has achieved state-of-the-art performance on two common datasets.
  arXiv  Detail & Related papers  (2024-12-24T16:38:04Z)
• Survey on Abstractive Text Summarization: Dataset, Models, and Metrics [0.8184895397419141]
  Transformer models are distinguished by their attention mechanisms, pretraining on general knowledge, and fine-tuning for downstream tasks. This survey examines the state of the art in text summarization models, with a specific focus on the abstractive summarization approach.
  arXiv  Detail & Related papers  (2024-12-22T21:18:40Z)
• Graph-DPEP: Decomposed Plug and Ensemble Play for Few-Shot Document Relation Extraction with Graph-of-Thoughts Reasoning [34.85741925091139]
  Graph-DPEP framework is grounded in the reasoning behind triplet explanation thoughts presented in natural language. We develop "ensemble-play", reapplying generation on the entire type list by leveraging the reasoning thoughts embedded in a sub-graph.
  arXiv  Detail & Related papers  (2024-11-05T07:12:36Z)
• RKadiyala at SemEval-2024 Task 8: Black-Box Word-Level Text Boundary Detection in Partially Machine Generated Texts [0.0]
  This paper introduces few reliable approaches for identifying which part of a given text is machine generated at a word level. We present a comparison with proprietary systems, performance of our model on unseen domains' and generators' texts. The findings reveal significant improvements in detection accuracy along with comparison on other aspects of detection capabilities.
  arXiv  Detail & Related papers  (2024-10-22T03:21:59Z)
• XPrompt:Explaining Large Language Model's Generation via Joint Prompt Attribution [26.639271355209104]
  Large Language Models (LLMs) have demonstrated impressive performances in complex text generation tasks. The contribution of the input prompt to the generated content still remains obscure to humans. We introduce a counterfactual explanation framework based on joint prompt attribution, XPrompt.
  arXiv  Detail & Related papers  (2024-05-30T18:16:41Z)
• Peering into the Mind of Language Models: An Approach for Attribution in Contextual Question Answering [9.86691461253151]
  We introduce a novel method for attribution in contextual question answering, leveraging the hidden state representations of large language models (LLMs) Our approach bypasses the need for extensive model retraining and retrieval model overhead, offering granular attributions and preserving the quality of generated answers. We present Verifiability-granular, an attribution dataset which has token level annotations for LLM generations in the contextual question answering setup.
  arXiv  Detail & Related papers  (2024-05-28T09:12:44Z)
• Exploration of Masked and Causal Language Modelling for Text Generation [6.26998839917804]
  This paper conducts an extensive comparison of Causal Language Modelling approaches for text generation tasks. We first employ quantitative metrics and then perform a qualitative human evaluation to analyse coherence and grammatical correctness. The results show that consistently outperforms CLM in text generation across all datasets.
  arXiv  Detail & Related papers  (2024-05-21T09:33:31Z)
• Language Models for Text Classification: Is In-Context Learning Enough? [54.869097980761595]
  Recent foundational language models have shown state-of-the-art performance in many NLP tasks in zero- and few-shot settings. An advantage of these models over more standard approaches is the ability to understand instructions written in natural language (prompts) This makes them suitable for addressing text classification problems for domains with limited amounts of annotated instances.
  arXiv  Detail & Related papers  (2024-03-26T12:47:39Z)
• generAItor: Tree-in-the-Loop Text Generation for Language Model Explainability and Adaptation [28.715001906405362]
  Large language models (LLMs) are widely deployed in various downstream tasks, e.g., auto-completion, aided writing, or chat-based text generation. We tackle this shortcoming by proposing a tree-in-the-loop approach, where a visual representation of the beam search tree is the central component for analyzing, explaining, and adapting the generated outputs. We present generAItor, a visual analytics technique, augmenting the central beam search tree with various task-specific widgets, providing targeted visualizations and interaction possibilities.
  arXiv  Detail & Related papers  (2024-03-12T13:09:15Z)
• ToBlend: Token-Level Blending With an Ensemble of LLMs to Attack AI-Generated Text Detection [6.27025292177391]
  ToBlend is a novel token-level ensemble text generation method to challenge the robustness of current AI-content detection approaches. We find ToBlend significantly drops the performance of most mainstream AI-content detection methods.
  arXiv  Detail & Related papers  (2024-02-17T02:25:57Z)
• SEED-Bench-2: Benchmarking Multimodal Large Language Models [67.28089415198338]
  Multimodal large language models (MLLMs) have recently demonstrated exceptional capabilities in generating not only texts but also images given interleaved multimodal inputs. SEED-Bench-2 comprises 24K multiple-choice questions with accurate human annotations, which spans 27 dimensions. We evaluate the performance of 23 prominent open-source MLLMs and summarize valuable observations.
  arXiv  Detail & Related papers  (2023-11-28T05:53:55Z)
• Language Model Decoding as Direct Metrics Optimization [87.68281625776282]
  Current decoding methods struggle to generate texts that align with human texts across different aspects. In this work, we frame decoding from a language model as an optimization problem with the goal of strictly matching the expected performance with human texts. We prove that this induced distribution is guaranteed to improve the perplexity on human texts, which suggests a better approximation to the underlying distribution of human texts.
  arXiv  Detail & Related papers  (2023-10-02T09:35:27Z)
• MAGE: Machine-generated Text Detection in the Wild [82.70561073277801]
  Large language models (LLMs) have achieved human-level text generation, emphasizing the need for effective AI-generated text detection. We build a comprehensive testbed by gathering texts from diverse human writings and texts generated by different LLMs. Despite challenges, the top-performing detector can identify 86.54% out-of-domain texts generated by a new LLM, indicating the feasibility for application scenarios.
  arXiv  Detail & Related papers  (2023-05-22T17:13:29Z)
• Large Language Models are Diverse Role-Players for Summarization Evaluation [82.31575622685902]
  A document summary's quality can be assessed by human annotators on various criteria, both objective ones like grammar and correctness, and subjective ones like informativeness, succinctness, and appeal. Most of the automatic evaluation methods like BLUE/ROUGE may be not able to adequately capture the above dimensions. We propose a new evaluation framework based on LLMs, which provides a comprehensive evaluation framework by comparing generated text and reference text from both objective and subjective aspects.
  arXiv  Detail & Related papers  (2023-03-27T10:40:59Z)
• Classifiers are Better Experts for Controllable Text Generation [63.17266060165098]
  We show that the proposed method significantly outperforms recent PPLM, GeDi, and DExperts on PPL and sentiment accuracy based on the external classifier of generated texts. The same time, it is also easier to implement and tune, and has significantly fewer restrictions and requirements.
  arXiv  Detail & Related papers  (2022-05-15T12:58:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.