# Towards Faithful and Robust LLM Specialists for Evidence-Based Question-Answering

arXiv: https://arxiv.org/abs/2402.08277 · HTML: https://mlsanity.com/paper/2402.08277/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 48 references that are in the map.
- First posted on arXiv 13 Feb 2024.

## Builds on (most cited first, 22 of 22)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [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)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://mlsanity.com/paper/2310.11511/) (2023)
- [Improving language models by retrieving from trillions of tokens](https://mlsanity.com/paper/2112.04426/) (2021)
- [FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation](https://mlsanity.com/paper/2305.14251/) (2023)
- [Enabling Large Language Models to Generate Text with Citations](https://mlsanity.com/paper/2305.14627/) (2023)
- [Unnatural Instructions: Tuning Language Models with (Almost) No Human Labor](https://mlsanity.com/paper/2212.09689/) (2022)
- [Evaluating Verifiability in Generative Search Engines](https://mlsanity.com/paper/2304.09848/) (2023)
- [ARES: An Automated Evaluation Framework for Retrieval-Augmented Generation Systems](https://mlsanity.com/paper/2311.09476/) (2023)
- [HoVer: A Dataset for Many-Hop Fact Extraction And Claim Verification](https://mlsanity.com/paper/2011.03088/) (2020)
- [Chatlaw: A Multi-Agent Legal Assistant based on a Role-Aligned Mixture-of-Experts Architecture](https://mlsanity.com/paper/2306.16092/) (2023)
- [A Survey of Large Language Models Attribution](https://mlsanity.com/paper/2311.03731/) (2023)
- [Do Large Language Models Know about Facts?](https://mlsanity.com/paper/2310.05177/) (2023)
- [Dynosaur: A Dynamic Growth Paradigm for Instruction-Tuning Data Curation](https://mlsanity.com/paper/2305.14327/) (2023)
- [CHATREPORT: Democratizing Sustainability Disclosure Analysis through LLM-based Tools](https://mlsanity.com/paper/2307.15770/) (2023)

## Built on by (most cited first, 11 of 11)

- [LongCite: Enabling LLMs to Generate Fine-grained Citations in Long-context QA](https://mlsanity.com/paper/2409.02897/) (2024)
- [How Susceptible are LLMs to Influence in Prompts?](https://mlsanity.com/paper/2408.11865/) (2024)
- [Source2Synth: Synthetic Data Generation and Curation Grounded in Real Data Sources](https://mlsanity.com/paper/2409.08239/) (2024)
- [Refining Input Guardrails: Enhancing LLM-as-a-Judge Efficiency Through Chain-of-Thought Fine-Tuning and Alignment](https://mlsanity.com/paper/2501.13080/) (2025)
- [Translate Policy to Language: Flow Matching Generated Rewards for LLM Explanations](https://mlsanity.com/paper/2502.12530/) (2025)
- [HIRAG: Hierarchical-Thought Instruction-Tuning Retrieval-Augmented Generation](https://mlsanity.com/paper/2507.05714/) (2025)
- [FISHNET: Financial Intelligence from Sub-querying, Harmonizing, Neural-Conditioning, Expert Swarms, and Task Planning](https://mlsanity.com/paper/2410.19727/) (2024)
- [Large Language Models as Search Engines: Societal Challenges](https://mlsanity.com/paper/2512.08946/) (2025)
- [Plan-MCTS: Plan Exploration for Action Exploitation in Web Navigation](https://mlsanity.com/paper/2602.14083/) (2026)
- [HypoChainer: A Collaborative System Combining LLMs and Knowledge Graphs for Hypothesis-Driven Scientific Discovery](https://mlsanity.com/paper/2507.17209/) (2025)
- [Call2Instruct: Automated Pipeline for Generating Q&A Datasets from Call Center Recordings for LLM Fine-Tuning](https://mlsanity.com/paper/2601.14263/) (2025)

## Abstract (arXiv)

Advances towards more faithful and traceable answers of Large Language Models (LLMs) are crucial for various research and practical endeavors. One avenue in reaching this goal is basing the answers on reliable sources. However, this Evidence-Based QA has proven to work insufficiently with LLMs in terms of citing the correct sources (source quality) and truthfully representing the information within sources (answer attributability). In this work, we systematically investigate how to robustly fine-tune LLMs for better source quality and answer attributability. Specifically, we introduce a data generation pipeline with automated data quality filters, which can synthesize diversified high-quality training and testing data at scale. We further introduce four test sets to benchmark the robustness of fine-tuned specialist models. Extensive evaluation shows that fine-tuning on synthetic data improves performance on both in- and out-of-distribution. Furthermore, we show that data quality, which can be drastically improved by proposed quality filters, matters more than quantity in improving Evidence-Based QA.