Search arXiv⌕ Search
Home/Archive/arXiv

arXiv · 2207.08083

Towards Explainability in NLP: Analyzing and Calculating Word Saliency through Word Properties

Jialiang Dong·Zhitao Guan·Longfei Wu·Zijian Zhang·Xiaojiang Du
View original source ↗Read source document ↗Export metadata ↓

Abstract

The wide use of black-box models in natural language processing brings great challenges to the understanding of the decision basis, the trustworthiness of the prediction results, and the improvement of the model performance. The words in text samples have properties that reflect their semantics and contextual information, such as the part of speech, the position, etc. These properties may have certain relationships with the word saliency, which is of great help for studying the explainability of the model predictions. In this paper, we explore the relationships between the word saliency and the word properties. According to the analysis results, we further establish a mapping model, Seq2Saliency, from the words in a text sample and their properties to the saliency values based on the idea of sequence tagging. In addition, we establish a new dataset called PrSalM, which contains each word in the text samples, the word properties, and the word saliency values. The experimental evaluations are conducted to analyze the saliency of words with different properties. The effectiveness of the Seq2Saliency model is verified.

Explore related subjects

cs.CL

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Jialiang Dong, Zhitao Guan, Longfei Wu, Zijian Zhang, Xiaojiang Du. 2022-09-02. Towards Explainability in NLP: Analyzing and Calculating Word Saliency through Word Properties. https://arxiv.org/abs/2207.08083

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

LiSeCo: Linear Semantic Control for Language Generation

The prevalence of Large Language Models (LLMs) in critical applications highlights the need for controlled language generation methods that are both computationally efficient and enjoy performance guarantees. To address this need, we use a common model of concept semantics as linearly represented in an LLM's latent space. In particular, we take the view that natural language generation traces a trajectory in this continuous semantic space, realized by the language model's hidden activations. This view permits a control-theoretic treatment of text generation in latent space, in which we propose Linear Semantic Control (LiSeCo), a lightweight, gradient-free intervention that dynamically steers trajectories away from regions corresponding to undesired meanings. In particular, we propose to directly intervene, in an online fashion, the activations of the token that is being generated in embedding space. Crucially, LiSeCo does not simply steer activations towards a desirable region. Instead, it relies on classical techniques from control theory to precisely control activations in a context-dependent way, and guarantees that they are brought into a specific pre-defined region of embedding space that corresponds to allowed semantics. The intervention is computed in closed form according to an optimal controller formulation, minimally impacting generation time. This control of the activations in embedding space allows for fine-grained steering of attributes of the generated sequence. We demonstrate that our approach is effective on different tasks -- toxicity, sentiment, and language (English/Spanish) steering -- while maintaining text quality.

cs.CL↗
arXiv2026

VMMU: A Vietnamese Multitask Multimodal Understanding and Reasoning Benchmark

We introduce VMMU, a Vietnamese Multitask Multimodal Understanding and Reasoning Benchmark designed to evaluate how vision-language models (VLMs) interpret and reason over visual and textual information beyond English. VMMU consists of 2.5k multimodal questions across 7 tasks, covering a diverse range of problem contexts, including STEM problem solving, data interpretation, rule-governed visual reasoning, and abstract visual reasoning. All questions require genuine multimodal integration, rather than reliance on text-only cues or OCR-based shortcuts. We evaluate a diverse set of state-of-the-art proprietary and open-source VLMs on VMMU. Despite strong Vietnamese OCR performance, proprietary models achieve only 66% mean accuracy. Further analysis shows that the primary source of failure is not OCR, but instead multimodal grounding and reasoning over text and visual evidence. Code and data are available at https://vmmu-bench.github.io/

cs.CL↗
arXiv2026

RapidUn: Influence-Driven Parameter Reweighting for Efficient Large Language Model Unlearning

Machine unlearning for large language models (LLMs) remains challenging because full retraining is costly, while approximate methods often struggle to remove targeted behaviors without degrading retained utility, especially under limited post-deployment supervision. We consider a practical PEFT setting for targeted behavioral contamination removal with a small forget set, a limited retain buffer, and LoRA-only updates, and propose RapidUn, an influence-guided framework that converts cross-sample influence estimates into fixed sample-specific weights for weighted LoRA unlearning. Across Llama-3-8B on Dolly-15k and Alpaca-57k, with cross-model validation on Mistral-7B + Dolly-15k, RapidUn achieves lower seen-trigger and OOD-trigger-family ASR than Fisher, GA, and LoReUn while maintaining competitive clean utility. On Llama-3-8B + Alpaca-57k, it achieves a 77x wall-clock speedup over the clean-corpus LoRA retraining reference. Complementary TOFU, semantic LLM-judge, and IFEval evaluations further support the effectiveness of influence-guided sample reweighting beyond the controlled trigger benchmark.

cs.CL↗