Post-training an LLM for RAG? Train on Self-Generated Demonstrations

• URL: http://arxiv.org/abs/2502.10596v2
• Date: Sat, 01 Mar 2025 06:33:01 GMT
• Title: Post-training an LLM for RAG? Train on Self-Generated Demonstrations
• Authors: Matthew Finlayson, Ilia Kulikov, Daniel M. Bikel, Barlas Oguz, Xilun Chen, Aasish Pappu,
• Abstract summary: Large language models (LLMs) often struggle with knowledge intensive NLP tasks.<n>Retrieval augmented generation (RAG) allows the model to leverage in-context information.<n>We propose a recipe for training RAG-enabled LLMs using self-generated demonstrations.
• Score: 19.972220654354494
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models (LLMs) often struggle with knowledge intensive NLP tasks, such as answering "Who won the latest World Cup?" because the knowledge they learn during training may be insufficient or outdated. Conditioning generation on retrieved documents -- a technique known as retrieval augmented generation (RAG) -- mitigates these shortcomings by allowing the model to leverage in-context information. Practitioners can improve LLM RAG performance by fine-tuning on retrieval-augmented instructions, but must beware that this can cause undesirable model behaviors like hallucinations. We attribute this degradation to the fact that the training data is likely to be out-of-distribution for the model and may suffer from quality issues, such as misalignment between retrievals and target responses (since retrievals are frequently added post-hoc). We propose a recipe for training RAG-enabled LLMs using self-generated demonstrations, thereby avoiding training on out-of-distribution text and integrating retrievals into the LLM responses. We evaluate our method on knowledge intensive question answering (QA) tasks and show that our method teaches LLMs to properly handle in-context retrievals and abstain from questions it will likely get wrong. Compared to conventional RA-IT methods, our method prevents model degradation in non-RAG settings while exhibiting superior QA performance.

Related papers

• An Analysis of Decoding Methods for LLM-based Agents for Faithful Multi-Hop Question Answering [44.41915467956464]
  Large Language Models (LLMs) frequently produce factually inaccurate outputs. This phenomenon limits their accuracy in knowledge-intensive NLP tasks. Recent research has explored training-free decoding strategies to improve the faithfulness of model generations.
  arXiv  Detail & Related papers  (2025-03-30T12:18:21Z)
• R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning [87.30285670315334]
  textbfR1-Searcher is a novel two-stage outcome-based RL approach designed to enhance the search capabilities of Large Language Models. Our framework relies exclusively on RL, without requiring process rewards or distillation for a cold start. Our experiments demonstrate that our method significantly outperforms previous strong RAG methods, even when compared to the closed-source GPT-4o-mini.
  arXiv  Detail & Related papers  (2025-03-07T17:14:44Z)
• How Much Knowledge Can You Pack into a LoRA Adapter without Harming LLM? [55.33467849079774]
  Low-rank adaptation (LoRA) is a popular and efficient training technique for updating or domain-specific adaptation of Large Language Models. We investigate how new facts can be incorporated into the LLM using LoRA without compromising the previously learned knowledge.
  arXiv  Detail & Related papers  (2025-02-20T12:31:03Z)
• Invar-RAG: Invariant LLM-aligned Retrieval for Better Generation [43.630437906898635]
  We propose a novel two-stage fine-tuning architecture called Invar-RAG. In the retrieval stage, an LLM-based retriever is constructed by integrating LoRA-based representation learning. In the generation stage, a refined fine-tuning method is employed to improve LLM accuracy in generating answers based on retrieved information.
  arXiv  Detail & Related papers  (2024-11-11T14:25:37Z)
• Teaching Models to Improve on Tape [30.330699770714165]
  Large Language Models (LLMs) often struggle when prompted to generate content under specific constraints. Recent works have shown that LLMs can benefit from such "corrective feedback" We introduce an RL framework for teaching models to use such rewards, by simulating interaction sessions, and rewarding the model according to its ability to satisfy the constraints.
  arXiv  Detail & Related papers  (2024-11-03T08:49:55Z)
• Unsupervised Information Refinement Training of Large Language Models for Retrieval-Augmented Generation [128.01050030936028]
  We propose an information refinement training method named InFO-RAG. InFO-RAG is low-cost and general across various tasks. It improves the performance of LLaMA2 by an average of 9.39% relative points.
  arXiv  Detail & Related papers  (2024-02-28T08:24:38Z)
• ActiveRAG: Autonomously Knowledge Assimilation and Accommodation through Retrieval-Augmented Agents [49.30553350788524]
  Retrieval-Augmented Generation (RAG) enables Large Language Models (LLMs) to leverage external knowledge. Existing RAG models often treat LLMs as passive recipients of information. We introduce ActiveRAG, a multi-agent framework that mimics human learning behavior.
  arXiv  Detail & Related papers  (2024-02-21T06:04:53Z)
• Where is the answer? Investigating Positional Bias in Language Model Knowledge Extraction [36.40833517478628]
  Large language models require updates to remain up-to-date or adapt to new domains. One key is memorizing the latest information in a way that the memorized information is extractable with a query prompt. Despite minimizing document perplexity during fine-tuning, LLMs struggle to extract information through a prompt sentence.
  arXiv  Detail & Related papers  (2024-02-16T06:29:16Z)
• ReEval: Automatic Hallucination Evaluation for Retrieval-Augmented Large Language Models via Transferable Adversarial Attacks [91.55895047448249]
  This paper presents ReEval, an LLM-based framework using prompt chaining to perturb the original evidence for generating new test cases. We implement ReEval using ChatGPT and evaluate the resulting variants of two popular open-domain QA datasets. Our generated data is human-readable and useful to trigger hallucination in large language models.
  arXiv  Detail & Related papers  (2023-10-19T06:37:32Z)
• Reflection-Tuning: Data Recycling Improves LLM Instruction-Tuning [79.32236399694077]
  Low-quality data in the training set are usually detrimental to instruction tuning. We propose a novel method, termed "reflection-tuning" This approach utilizes an oracle LLM to recycle the original training data by introspecting and enhancing the quality of instructions and responses in the data.
  arXiv  Detail & Related papers  (2023-10-18T05:13:47Z)
• In-Context Unlearning: Language Models as Few Shot Unlearners [27.962361828354716]
  We propose a new class of unlearning methods for Large Language Models (LLMs) This method unlearns instances from the model by simply providing specific kinds of inputs in context, without the need to update model parameters. Our experimental results demonstrate that in-context unlearning performs on par with, or in some cases outperforms other state-of-the-art methods that require access to model parameters.
  arXiv  Detail & Related papers  (2023-10-11T15:19:31Z)
• LaGR-SEQ: Language-Guided Reinforcement Learning with Sample-Efficient Querying [71.86163159193327]
  Large language models (LLMs) have recently demonstrated their impressive ability to provide context-aware responses via text. This ability could potentially be used to predict plausible solutions in sequential decision making tasks pertaining to pattern completion. We introduce LaGR, which uses this predictive ability of LLMs to propose solutions to tasks that have been partially completed by a primary reinforcement learning (RL) agent.
  arXiv  Detail & Related papers  (2023-08-21T02:07:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.