paper-with-me

Papers

Learning Interpretable Text Signals for Structured Responses

2026-06-24 · Cixiao Jiang, Ben Powell, Niall MacKay arxiv

Textual data are often collected alongside structured response variables, but prediction and interpretation are commonly treated as separate tasks. This paper studies rating prediction as an initial case of interpretable text-response modelling, where the aim is to learn textual representations that are both semantically meaningful and aligned with an external response. We propose a joint non-negative matrix factorisation and binomial regression model, in which the document-topic representation is learned from both text reconstruction and rating prediction. Simulation experiments and a real-world review dataset show that the model can recover stable response-relevant textual signals and achieve competitive performance against linear and ridge regression baselines. The framework provides a practical step towards interpretable modelling of text-linked outcomes, with potential extensions to other response types beyond bounded ratings.

📄 PDF Abstract BibTeX arXiv:2606.25268

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

In your own words: computationally identifying interpretable themes in free-text survey data

2026-03-27 · Jenny S Wang, Aliya Saperstein, Emma Pierson arxiv

Free-text survey responses can provide nuance often missed by structured questions, but remain difficult to statistically analyze. To address this, we introduce In Your Own Words, a computational framework for explorator…

SEAR: Schema-Based Evaluation and Routing for LLM Gateways

2026-03-20 · Zecheng Zhang, Han Zheng, Yue Xu arxiv

Evaluating production LLM responses and routing requests across providers in LLM gateways requires fine-grained quality signals and operationally grounded decisions. To address this gap, we present SEAR, a schema-based e…

Safety is Not Only About Refusal: Reasoning-Enhanced Fine-tuning for Interpretable LLM Safety

2025-03-06 · Yuyou Zhang, Miao Li, William Han, Yihang Yao 외

Large Language Models (LLMs) are vulnerable to jailbreak attacks that exploit weaknesses in traditional safety alignment, which often relies on rigid refusal heuristics or representation engineering to block harmful outp…

Decision MakingSafety Alignment

Dual Knowledge-Enhanced Two-Stage Reasoner for Multimodal Dialog Systems

2025-09-09 · Xiaolin Chen, Xuemeng Song, Haokun Wen, Weili Guan 외 arxiv

Textual response generation is pivotal for multimodal \mbox{task-oriented} dialog systems, which aims to generate proper textual responses based on the multimodal context. While existing efforts have demonstrated remarka…

Response Generation

OmniTrace: A Unified Framework for Generation-Time Attribution in Omni-Modal LLMs

2026-03-20 · Qianqi Yan, Yichen Guo, Ching-Chen Kuo, Shan Jiang 외 arxiv

Modern multimodal large language models (MLLMs) generate fluent responses from interleaved text, image, audio, and video inputs. However, identifying which input sources support each generated statement remains an open c…

multimodal generation