paper-with-me

Papers

Conformal Linguistic Calibration: Trading-off between Factuality and Specificity

2025-02-26 · Zhengping Jiang, Anqi Liu, Benjamin Van Durme

Language model outputs are not always reliable, thus prompting research into how to adapt model responses based on uncertainty. Common approaches include: \emph{abstention}, where models refrain from generating responses when uncertain; and \emph{linguistic calibration}, where models hedge their statements using uncertainty quantifiers. However, abstention can withhold valuable information, while linguistically calibrated responses are often challenging to leverage in downstream tasks. We propose a unified view, Conformal Linguistic Calibration (CLC), which reinterprets linguistic calibration as \emph{answer set prediction}. First we present a framework connecting abstention and linguistic calibration through the lens of linguistic pragmatics. We then describe an implementation of CLC that allows for controlling the level of imprecision in model responses. Results demonstrate our method produces calibrated outputs with conformal guarantees on factual accuracy. Further, our approach enables fine-tuning models to perform uncertainty-aware adaptive claim rewriting, offering a controllable balance between factuality and specificity.

📄 PDF Abstract BibTeX arXiv:2502.19110

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage ModellingSpecificity

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

Is Conformal Factuality for RAG-based LLMs Robust? Novel Metrics and Systematic Insights

2026-03-17 · Yi Chen, Daiwei Chen, Sukrut Madhav Chikodikar, Caitlyn Heqi Yin 외 arxiv

Large language models (LLMs) frequently hallucinate, limiting their reliability in knowledge-intensive applications. Retrieval-augmented generation (RAG) and conformal factuality have emerged as potential ways to address…

Multi-LLM Adaptive Conformal Inference for Reliable LLM Responses

2026-02-01 · Kangjun Noh, Seongchan Lee, Ilmun Kim, Kyungwoo Song arxiv

Ensuring factuality is essential for the safe use of Large Language Models (LLMs) in high-stakes domains such as medicine and law. Conformal inference provides distribution-free guarantees, but existing approaches are ei…

PromptShift-CRC: Drift-Aware Conformal Risk Control for Foundation Models Under Prompt and Domain Shift

2026-06-14 · Jeffery Opoku, David Banahene arxiv

Foundation models are now used in settings where the prompts they receive can change quickly. Users change, topics change, policies change, and the model may suddenly face a kind of request that was rare in the calibrati…

Question Answering

Adaptive Conformal Prediction for Improving Factuality of Generations by Large Language Models

2026-04-15 · Aleksandr Rubashevskii, Dzianis Piatrashyn, Preslav Nakov, Maxim Panov arxiv

Large language models (LLMs) are prone to generating factually incorrect outputs. Recent work has applied conformal prediction to provide uncertainty estimates and statistical guarantees for the factuality of LLM generat…

Question Answering

Inference-Time Conformal Reasoning with Valid Factuality Control for Large Language Models

2026-06-07 · Ting Wang, Yuanjie Shi, Yan Yan, Huan Zhang arxiv

Large language models (LLMs) increasingly perform multi-step reasoning, where intermediate claims form implicit directed acyclic graphs whose node correctness is structurally conditioned on their ancestors. This makes fa…

Graph Generation