# Harnessing RLHF for Robust Unanswerability Recognition and Trustworthy Response Generation in LLMs

arXiv: https://arxiv.org/abs/2507.16951 · HTML: https://mlsanity.com/paper/2507.16951/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Preference alignment for recommenders and RAG, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 20 of its 25 references that are in the map.
- First posted on arXiv 22 Jul 2025.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Preference alignment for recommenders and RAG](https://mlsanity.com/alignment/preference-alignment-for-recommenders-and-rag/)

## Builds on (most cited first, 20 of 20)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions](https://mlsanity.com/paper/2311.05232/) (2023)
- [Evaluating the Factual Consistency of Abstractive Text Summarization](https://mlsanity.com/paper/1910.12840/) (2019)
- [Visual In-Context Learning for Large Vision-Language Models](https://mlsanity.com/paper/2402.11574/) (2024)
- [Language Models with Image Descriptors are Strong Few-Shot Video-Language Learners](https://mlsanity.com/paper/2205.10747/) (2022)
- [How Does BERT Answer Questions? A Layer-Wise Analysis of Transformer Representations](https://mlsanity.com/paper/1909.04925/) (2019)
- [ClarET: Pre-training a Correlation-Aware Context-To-Event Transformer for Event-Centric Generation and Classification](https://mlsanity.com/paper/2203.02225/) (2022)
- [Rethinking Visual Dependency in Long-Context Reasoning for Large Vision-Language Models](https://mlsanity.com/paper/2410.19732/) (2024)
- [EventBERT: A Pre-Trained Model for Event Correlation Reasoning](https://mlsanity.com/paper/2110.06533/) (2021)
- [Draw ALL Your Imagine: A Holistic Benchmark and Agent Framework for Complex Instruction-based Image Generation](https://mlsanity.com/paper/2505.24787/) (2025)
- [OLAPH: Improving Factuality in Biomedical Long-form Question Answering](https://mlsanity.com/paper/2405.12701/) (2024)
- [InstructPatentGPT: Training patent language models to follow instructions with human feedback](https://mlsanity.com/paper/2406.16897/) (2024)
- [Uncertainty-aware Language Modeling for Selective Question Answering](https://mlsanity.com/paper/2311.15451/) (2023)
- [U-shaped and Inverted-U Scaling behind Emergent Abilities of Large Language Models](https://mlsanity.com/paper/2410.01692/) (2024)
- [Say What I Want: Towards the Dark Side of Neural Dialogue Models](https://mlsanity.com/paper/1909.06044/) (2019)
- [Hint-enhanced In-Context Learning wakes Large Language Models up for knowledge-intensive tasks](https://mlsanity.com/paper/2311.01949/) (2023)

## Built on by (most cited first, 3 of 3)

- [Rewarding Intellectual Humility Learning When Not To Answer In Large Language Models](https://mlsanity.com/paper/2601.20126/) (2026)
- [Understanding Why Language Models Hallucinate: Testing Reasoning Against Priors](https://mlsanity.com/paper/2607.00447/) (2026)
- [Listen to the Layers: Mitigating Hallucinations with Inter-Layer Disagreement](https://mlsanity.com/paper/2602.09486/) (2026)

## Abstract (arXiv)

Conversational Information Retrieval (CIR) systems, while offering intuitive access to information, face a significant challenge: reliably handling unanswerable questions to prevent the generation of misleading or hallucinated content. Traditional approaches often rely on external classifiers, which can introduce inconsistencies with the core generative Large Language Models (LLMs). This paper introduces Self-Aware LLM for Unanswerability (SALU), a novel approach that deeply integrates unanswerability detection directly within the LLM's generative process. SALU is trained using a multi-task learning framework for both standard Question Answering (QA) and explicit abstention generation for unanswerable queries. Crucially, it incorporates a confidence-score-guided reinforcement learning with human feedback (RLHF) phase, which explicitly penalizes hallucinated responses and rewards appropriate abstentions, fostering intrinsic self-awareness of knowledge boundaries. Through extensive experiments on our custom-built C-IR_Answerability dataset, SALU consistently outperforms strong baselines, including hybrid LLM-classifier systems, in overall accuracy for correctly answering or abstaining from questions. Human evaluation further confirms SALU's superior reliability, achieving high scores in factuality, appropriate abstention, and, most importantly, a dramatic reduction in hallucination, demonstrating its ability to robustly "know when to say 'I don't know'."