# Mitigating Knowledge Conflicts in Language Model-Driven Question Answering

arXiv: https://arxiv.org/abs/2411.11344 · HTML: https://mlsanity.com/paper/2411.11344/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 43 references that are in the map.
- First posted on arXiv 18 Nov 2024.

## Builds on (most cited first, 29 of 29)

- [VQA: Visual Question Answering](https://mlsanity.com/paper/1505.00468/) (2015)
- [Extracting Training Data from Large Language Models](https://mlsanity.com/paper/2012.07805/) (2020)
- [Reading Wikipedia to Answer Open-Domain Questions](https://mlsanity.com/paper/1704.00051/) (2017)
- [CTRL: A Conditional Transformer Language Model for Controllable Generation](https://mlsanity.com/paper/1909.05858/) (2019)
- [Neural Text Generation with Unlikelihood Training](https://mlsanity.com/paper/1908.04319/) (2019)
- [Entity-Based Knowledge Conflicts in Question Answering](https://mlsanity.com/paper/2109.05052/) (2021)
- [NewsQA: A Machine Comprehension Dataset](https://mlsanity.com/paper/1611.09830/) (2016)
- [K-Adapter: Infusing Knowledge into Pre-Trained Models with Adapters](https://mlsanity.com/paper/2002.01808/) (2020)
- [ToTTo: A Controlled Table-To-Text Generation Dataset](https://mlsanity.com/paper/2004.14373/) (2020)
- [MultiModalQA: Complex Question Answering over Text, Tables and Images](https://mlsanity.com/paper/2104.06039/) (2021)
- [Hurdles to Progress in Long-form Question Answering](https://mlsanity.com/paper/2103.06332/) (2021)
- [The Curious Case of Hallucinations in Neural Machine Translation](https://mlsanity.com/paper/2104.06683/) (2021)
- [Controlling Linguistic Style Aspects in Neural Language Generation](https://mlsanity.com/paper/1707.02633/) (2017)
- [Handling Divergent Reference Texts when Evaluating Table-to-Text Generation](https://mlsanity.com/paper/1906.01081/) (2019)
- [Long Short-Term Memory Based Recurrent Neural Network Architectures for Large Vocabulary Speech Recognition](https://mlsanity.com/paper/1402.1128/) (2014)
- [Learning to Compose Neural Networks for Question Answering](https://mlsanity.com/paper/1601.01705/) (2016)
- [Common Sense or World Knowledge? Investigating Adapter-Based Knowledge Injection into Pretrained Transformers](https://mlsanity.com/paper/2005.11787/) (2020)
- [Prototypical Reward Network for Data-Efficient RLHF](https://mlsanity.com/paper/2406.06606/) (2024)
- [Real-Time Idling Vehicles Detection using Combined Audio-Visual Deep Learning](https://mlsanity.com/paper/2305.14579/) (2023)
- [Efficient Fine-Tuning of Large Language Models for Automated Medical Documentation](https://mlsanity.com/paper/2409.09324/) (2024)
- [Unsupervised Enrichment of Persona-grounded Dialog with Background Stories](https://mlsanity.com/paper/2106.08364/) (2021)
- [SDRTV-to-HDRTV via Hierarchical Dynamic Context Feature Mapping](https://mlsanity.com/paper/2207.00319/) (2022)
- [Machine Learning-Based Research on the Adaptability of Adolescents to Online Education](https://mlsanity.com/paper/2408.16849/) (2024)
- [Research on Improved U-net Based Remote Sensing Image Segmentation Algorithm](https://mlsanity.com/paper/2408.12672/) (2024)
- [Enhanced Self-Checkout System for Retail Based on Improved YOLOv10](https://mlsanity.com/paper/2407.21308/) (2024)
- [Integration of Mamba and Transformer -- MAT for Long-Short Range Time Series Forecasting with Application to Weather Dynamics](https://mlsanity.com/paper/2409.08530/) (2024)
- [KMIR: A Benchmark for Evaluating Knowledge Memorization, Identification and Reasoning Abilities of Language Models](https://mlsanity.com/paper/2202.13529/) (2022)
- [Optimization and Application of Cloud-based Deep Learning Architecture for Multi-Source Data Prediction](https://mlsanity.com/paper/2410.12642/) (2024)
- [Alphanetv4: Alpha Mining Model](https://mlsanity.com/paper/2411.04409/) (2024)

## Built on by (most cited first, 1 of 1)

- [Enhanced Recommendation Combining Collaborative Filtering and Large Language Models](https://mlsanity.com/paper/2412.18713/) (2024)

## Abstract (arXiv)

In the context of knowledge-driven seq-to-seq generation tasks, such as document-based question answering and document summarization systems, two fundamental knowledge sources play crucial roles: the inherent knowledge embedded within model parameters and the external knowledge obtained through context. Recent studies revealed a significant challenge: when there exists a misalignment between the model's inherent knowledge and the ground truth answers in training data, the system may exhibit problematic behaviors during inference, such as ignoring input context, or generating unfaithful content. Our investigation proposes a strategy to minimize hallucination by building explicit connection between source inputs and generated outputs. We specifically target a common hallucination pattern in question answering, examining how the correspondence between entities and their contexts during model training influences the system's performance at inference time.