paper-with-me

홈 › Papers

Does Faithfulness-Guided Alignment Hurt Accuracy? Unlocking Accurate and Faithful Post-Retrieval Reasoning

2026-02-01 · Yu Liu, Wenxiao Zhang, Diandian Guo, Cong Cao, Fangfang Yuan, Qiang Sun, Yanbing Liu, Jin B. Hong, Zhiyuan Ma arxiv

Retrieval-augmented generation (RAG) can achieve strong answer accuracy on multi-hop questions, but outcome-level rewards often leave reasoning traces weakly grounded and difficult to audit. Under noisy retrieval, models may exhibit right-answer-wrong-reason failures, where the final answer is correct but the supporting rationale exploits shortcuts or unsupported evidence. We therefore ask whether faithfulness-guided alignment hurts answer accuracy in post-retrieval reasoning. To study this question, we propose CRAFT (Calibrated Reasoning with Answer-Faithful Traces), a reinforcement learning framework for the response-generation stage of retrieval-augmented multi-hop question answering. CRAFT trains models to produce structured reasoning traces with configurable auditability, while combining deterministic rewards for format compliance, answer correctness, and citation validity with a judge-based reward for semantic faithfulness. Experiments across model scales and benchmarks show that CRAFT unlocks task-specific reasoning capacity from 1.5B upward, improving both answer accuracy and Faithfulness; at 0.5B, performance remains sharply template-dependent. At 7B, CRAFT improves Faithfulness over the Base model in all evaluated settings and remains competitive with strong closed-source models. Code is available at https://github.com/Ameame1/CRAFT.

📄 PDF Abstract BibTeX arXiv:2602.01348

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-hop Question AnsweringReinforcement LearningResponse Generation

Similar Papers 제목 키워드 기반

Evaluating Human Alignment and Model Faithfulness of LLM Rationale

2024-06-28 · Mohsen Fayyaz, Fan Yin, Jiao Sun, Nanyun Peng

We study how well large language models (LLMs) explain their generations through rationales -- a set of tokens extracted from the input text that reflect the decision-making process of LLMs. Specifically, we systematical…

Decision Making

Evaluating Reasoning Faithfulness in Medical Vision-Language Models using Multimodal Perturbations

2025-10-13 · Johannes Moll, Markus Graf, Tristan Lemke, Nicolas Lenhart 외 arxiv

Vision-language models (VLMs) often produce chain-of-thought (CoT) explanations that sound plausible yet fail to reflect the underlying decision process, undermining trust in high-stakes clinical use. Existing evaluation…

X-ray Visual Question Answering

Improving Diffusion-Based Image Editing Faithfulness via Guidance and Scheduling

2025-06-26 · Hansam Cho, Seoung Bum Kim

Text-guided diffusion models have become essential for high-quality image synthesis, enabling dynamic image editing. In image editing, two crucial aspects are editability, which determines the extent of modification, and…

Image GenerationScheduling

An Empirical Study of Counterfactual Self-Explanations in LLMs

2026-09-15 · Giannis Kalyvas, Giorgos Filandrianos, Orfeas Menis Mastromichalakis, Vassilis Lyberatos 외 arxiv

Large language models can easily generate explanations for their own outputs, but such self-explanations are not necessarily faithful to the model's behavior. We study this issue through counterfactual self-explanations,…

Natural Language InferenceSentiment Analysis

Gaussian Guided IoU: A Better Metric for Balanced Learning on Object Detection

2021-03-25 · Shengkai Wu, Jinrong Yang, Hangcheng Yu, Lijun Gou 외

For most of the anchor-based detectors, Intersection over Union(IoU) is widely utilized to assign targets for the anchors during training. However, IoU pays insufficient attention to the closeness of the anchor's center …

object-detectionObject Detection