Jointly Generating and Attributing Answers using Logits of Document-Identifier Tokens
Despite their impressive performances, Large Language Models (LLMs) remain prone to hallucination, which critically undermines their trustworthiness. While most of the previous work focused on tackling answer and attribution correctness, a recent line of work investigated faithfulness, with a focus on leveraging internal model signals to reflect a model's actual decision-making process while generating the answer. Nevertheless, these methods induce additional latency and have shown limitations in directly aligning token generation with attribution generation. In this paper, we introduce LoDIT, a method that jointly generates and faithfully attributes answers in RAG by leveraging specific token logits during generation. It consists of two steps: (1) marking the documents with specific token identifiers and then leveraging the logits of these tokens to estimate the contribution of each document to the answer during generation, and (2) aggregating these contributions into document attributions. Experiments on a trustworthiness-focused attributed text-generation benchmark, Trust-Align, show that LoDIT significantly outperforms state-of-the-art models on several metrics. Finally, an in-depth analysis of LoDIT shows both its efficiency in terms of latency and its robustness in different settings.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Evaluation of Attribution Bias in Retrieval-Augmented Large Language Models
Attributing answers to source documents is an approach used to enhance the verifiability of a model's output in retrieval augmented generation (RAG). Prior work has mainly focused on improving and evaluating the attribut…
AttributecounterfactualRAGRetrieval+2Enhancing Post-Hoc Attributions in Long Document Comprehension via Coarse Grained Answer Decomposition
Accurately attributing answer text to its source document is crucial for developing a reliable question-answering system. However, attribution for long documents remains largely unexplored. Post-hoc attribution systems a…
In-Context LearningQuestion AnsweringAttributing Culture-Conditioned Generations to Pretraining Corpora
In open-ended generative tasks like narrative writing or dialogue, large language models often exhibit cultural biases, showing limited knowledge and generating templated outputs for less prevalent cultures. Recent works…
MemorizationTarget Prompting for Information Extraction with Vision Language Model
The recent trend in the Large Vision and Language model has brought a new change in how information extraction systems are built. VLMs have set a new benchmark with their State-of-the-art techniques in understanding docu…
Language ModelingLanguage ModellingQuestion AnsweringMultAttnAttrib: Training-Free Multimodal Attribution in Long Document Question Answering
As grounded QA systems are increasingly deployed in AI assistants, accurately attributing generated answers to evidence is critical for user trust and model safety. While unimodal attributions have been explored in depth…
Question Answering