TracLLM: A Generic Framework for Attributing Long Context LLMs

• URL: http://arxiv.org/abs/2506.04202v3
• Date: Thu, 26 Jun 2025 16:09:36 GMT
• Title: TracLLM: A Generic Framework for Attributing Long Context LLMs
• Authors: Yanting Wang, Wei Zou, Runpeng Geng, Jinyuan Jia,
• Abstract summary: We develop TracLLM, the first generic context traceback framework tailored to long context LLMs.<n>Our framework can improve the effectiveness and efficiency of existing feature attribution methods.<n>Our evaluation results show TracLLM can effectively identify texts in a long context that lead to the output of an LLM.
• Score: 34.802736332993994
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Long context large language models (LLMs) are deployed in many real-world applications such as RAG, agent, and broad LLM-integrated applications. Given an instruction and a long context (e.g., documents, PDF files, webpages), a long context LLM can generate an output grounded in the provided context, aiming to provide more accurate, up-to-date, and verifiable outputs while reducing hallucinations and unsupported claims. This raises a research question: how to pinpoint the texts (e.g., sentences, passages, or paragraphs) in the context that contribute most to or are responsible for the generated output by an LLM? This process, which we call context traceback, has various real-world applications, such as 1) debugging LLM-based systems, 2) conducting post-attack forensic analysis for attacks (e.g., prompt injection attack, knowledge corruption attacks) to an LLM, and 3) highlighting knowledge sources to enhance the trust of users towards outputs generated by LLMs. When applied to context traceback for long context LLMs, existing feature attribution methods such as Shapley have sub-optimal performance and/or incur a large computational cost. In this work, we develop TracLLM, the first generic context traceback framework tailored to long context LLMs. Our framework can improve the effectiveness and efficiency of existing feature attribution methods. To improve the efficiency, we develop an informed search based algorithm in TracLLM. We also develop contribution score ensemble/denoising techniques to improve the accuracy of TracLLM. Our evaluation results show TracLLM can effectively identify texts in a long context that lead to the output of an LLM. Our code and data are at: https://github.com/Wang-Yanting/TracLLM.

Related papers

• AttnTrace: Attention-based Context Traceback for Long-Context LLMs [30.472252134918815]
  We propose AttnTrace, a new context traceback method based on the attention weights produced by an LLM for a prompt.<n>The results demonstrate that AttnTrace is more accurate and efficient than existing state-of-the-art context traceback methods.
  arXiv  Detail & Related papers  (2025-08-05T17:56:51Z)
• LightPROF: A Lightweight Reasoning Framework for Large Language Model on Knowledge Graph [57.382255728234064]
  Large Language Models (LLMs) have impressive capabilities in text understanding and zero-shot reasoning.<n> Knowledge Graphs (KGs) provide rich and reliable contextual information for the reasoning process of LLMs.<n>We propose a novel Lightweight and efficient Prompt learning-ReasOning Framework for KGQA (LightPROF)
  arXiv  Detail & Related papers  (2025-04-04T03:03:47Z)
• An Empirical Study on Commit Message Generation using LLMs via In-Context Learning [26.39743339039473]
  Commit messages concisely describe code changes in natural language.<n>We propose to borrow the weapon of large language models (LLMs) and in-context learning (ICL) to generate commit messages.
  arXiv  Detail & Related papers  (2025-02-26T07:47:52Z)
• 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)
• Get my drift? Catching LLM Task Drift with Activation Deltas [55.75645403965326]
  Task drift allows attackers to exfiltrate data or influence the LLM's output for other users.<n>We show that a simple linear classifier can detect drift with near-perfect ROC AUC on an out-of-distribution test set.<n>We observe that this approach generalizes surprisingly well to unseen task domains, such as prompt injections, jailbreaks, and malicious instructions.
  arXiv  Detail & Related papers  (2024-06-02T16:53:21Z)
• 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)
• Blinded by Generated Contexts: How Language Models Merge Generated and Retrieved Contexts When Knowledge Conflicts? [45.233517779029334]
  We identify whether responses are attributed to generated or retrieved contexts. Experiments reveal a significant bias in several LLMs to favor generated contexts, even when they provide incorrect information.
  arXiv  Detail & Related papers  (2024-01-22T12:54:04Z)
• LLMRefine: Pinpointing and Refining Large Language Models via Fine-Grained Actionable Feedback [65.84061725174269]
  Recent large language models (LLM) are leveraging human feedback to improve their generation quality. We propose LLMRefine, an inference time optimization method to refine LLM's output. We conduct experiments on three text generation tasks, including machine translation, long-form question answering (QA), and topical summarization. LLMRefine consistently outperforms all baseline approaches, achieving improvements up to 1.7 MetricX points on translation tasks, 8.1 ROUGE-L on ASQA, 2.2 ROUGE-L on topical summarization.
  arXiv  Detail & Related papers  (2023-11-15T19:52:11Z)
• LLatrieval: LLM-Verified Retrieval for Verifiable Generation [67.93134176912477]
  Verifiable generation aims to let the large language model (LLM) generate text with supporting documents. We propose LLatrieval (Large Language Model Verified Retrieval), where the LLM updates the retrieval result until it verifies that the retrieved documents can sufficiently support answering the question. Experiments show that LLatrieval significantly outperforms extensive baselines and achieves state-of-the-art results.
  arXiv  Detail & Related papers  (2023-11-14T01:38:02Z)
• Assessing the Reliability of Large Language Model Knowledge [78.38870272050106]
  Large language models (LLMs) have been treated as knowledge bases due to their strong performance in knowledge probing tasks. How do we evaluate the capabilities of LLMs to consistently produce factually correct answers? We propose MOdel kNowledge relIabiliTy scORe (MONITOR), a novel metric designed to directly measure LLMs' factual reliability.
  arXiv  Detail & Related papers  (2023-10-15T12:40:30Z)

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.