Interpreting Multilingual and Document-Length Sensitive Relevance Computations in Neural Retrieval Models through Axiomatic Causal Interventions

• URL: http://arxiv.org/abs/2505.02154v1
• Date: Sun, 04 May 2025 15:30:45 GMT
• Title: Interpreting Multilingual and Document-Length Sensitive Relevance Computations in Neural Retrieval Models through Axiomatic Causal Interventions
• Authors: Oliver Savolainen, Dur e Najaf Amjad, Roxana Petcu,
• Abstract summary: This study analyzes and extends the paper "Axiomatic Causal Interventions for Reverse Engineering Relevance in Neural Retrieval Models"<n>We reproduce key experiments from the original paper, confirming that information on query terms is captured in the model encoding.<n>We extend this work by applying activation patching to Spanish and Chinese datasets and by exploring whether document-length information is encoded in the model as well.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This reproducibility study analyzes and extends the paper "Axiomatic Causal Interventions for Reverse Engineering Relevance Computation in Neural Retrieval Models," which investigates how neural retrieval models encode task-relevant properties such as term frequency. We reproduce key experiments from the original paper, confirming that information on query terms is captured in the model encoding. We extend this work by applying activation patching to Spanish and Chinese datasets and by exploring whether document-length information is encoded in the model as well. Our results confirm that the designed activation patching method can isolate the behavior to specific components and tokens in neural retrieval models. Moreover, our findings indicate that the location of term frequency generalizes across languages and that in later layers, the information for sequence-level tasks is represented in the CLS token. The results highlight the need for further research into interpretability in information retrieval and reproducibility in machine learning research. Our code is available at https://github.com/OliverSavolainen/axiomatic-ir-reproduce.

Related papers

• Memorization or Interpolation ? Detecting LLM Memorization through Input Perturbation Analysis [8.725781605542675]
  Large Language Models (LLMs) achieve remarkable performance through training on massive datasets.<n>LLMs can exhibit concerning behaviors such as verbatim reproduction of training data rather than true generalization.<n>This paper introduces PEARL, a novel approach for detecting memorization in LLMs.
  arXiv  Detail & Related papers  (2025-05-05T20:42:34Z)
• Exploring Training and Inference Scaling Laws in Generative Retrieval [50.82554729023865]
  Generative retrieval reformulates retrieval as an autoregressive generation task, where large language models generate target documents directly from a query.<n>We systematically investigate training and inference scaling laws in generative retrieval, exploring how model size, training data scale, and inference-time compute jointly influence performance.
  arXiv  Detail & Related papers  (2025-03-24T17:59:03Z)
• LatentQA: Teaching LLMs to Decode Activations Into Natural Language [72.87064562349742]
  We introduce LatentQA, the task of answering open-ended questions about model activations in natural language.<n>We propose Latent Interpretation Tuning (LIT), which finetunes a decoder LLM on a dataset of activations and associated question-answer pairs.<n>Our decoder also specifies a differentiable loss that we use to control models, such as debiasing models on stereotyped sentences and controlling the sentiment of generations.
  arXiv  Detail & Related papers  (2024-12-11T18:59:33Z)
• Pointwise Mutual Information as a Performance Gauge for Retrieval-Augmented Generation [78.28197013467157]
  We show that the pointwise mutual information between a context and a question is an effective gauge for language model performance.<n>We propose two methods that use the pointwise mutual information between a document and a question as a gauge for selecting and constructing prompts that lead to better performance.
  arXiv  Detail & Related papers  (2024-11-12T13:14:09Z)
• Investigating the Timescales of Language Processing with EEG and Language Models [0.0]
  This study explores the temporal dynamics of language processing by examining the alignment between word representations from a pre-trained language model and EEG data. Using a Temporal Response Function (TRF) model, we investigate how neural activity corresponds to model representations across different layers. Our analysis reveals patterns in TRFs from distinct layers, highlighting varying contributions to lexical and compositional processing.
  arXiv  Detail & Related papers  (2024-06-28T12:49:27Z)
• RegaVAE: A Retrieval-Augmented Gaussian Mixture Variational Auto-Encoder for Language Modeling [79.56442336234221]
  We introduce RegaVAE, a retrieval-augmented language model built upon the variational auto-encoder (VAE) It encodes the text corpus into a latent space, capturing current and future information from both source and target text. Experimental results on various datasets demonstrate significant improvements in text generation quality and hallucination removal.
  arXiv  Detail & Related papers  (2023-10-16T16:42:01Z)
• A Mechanistic Interpretation of Arithmetic Reasoning in Language Models using Causal Mediation Analysis [128.0532113800092]
  We present a mechanistic interpretation of Transformer-based LMs on arithmetic questions. This provides insights into how information related to arithmetic is processed by LMs.
  arXiv  Detail & Related papers  (2023-05-24T11:43:47Z)
• Measures of Information Reflect Memorization Patterns [53.71420125627608]
  We show that the diversity in the activation patterns of different neurons is reflective of model generalization and memorization. Importantly, we discover that information organization points to the two forms of memorization, even for neural activations computed on unlabelled in-distribution examples.
  arXiv  Detail & Related papers  (2022-10-17T20:15:24Z)
• An Empirical Investigation of Commonsense Self-Supervision with Knowledge Graphs [67.23285413610243]
  Self-supervision based on the information extracted from large knowledge graphs has been shown to improve the generalization of language models. We study the effect of knowledge sampling strategies and sizes that can be used to generate synthetic data for adapting language models.
  arXiv  Detail & Related papers  (2022-05-21T19:49:04Z)
• An Evaluation of Recent Neural Sequence Tagging Models in Turkish Named Entity Recognition [5.161531917413708]
  We propose a transformer-based network with a conditional random field layer that leads to the state-of-the-art result. Our study contributes to the literature that quantifies the impact of transfer learning on processing morphologically rich languages.
  arXiv  Detail & Related papers  (2020-05-14T06:54:07Z)
• Data Mining in Clinical Trial Text: Transformers for Classification and Question Answering Tasks [2.127049691404299]
  This research applies advances in natural language processing to evidence synthesis based on medical texts. The main focus is on information characterized via the Population, Intervention, Comparator, and Outcome (PICO) framework. Recent neural network architectures based on transformers show capacities for transfer learning and increased performance on downstream natural language processing tasks.
  arXiv  Detail & Related papers  (2020-01-30T11:45:59Z)

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.