When Summaries Distort Decisions: Information Fidelity in LLM-Compressed Financial Analysis

• URL: http://arxiv.org/abs/2606.29251v1
• Date: Sun, 28 Jun 2026 07:44:54 GMT
• Title: When Summaries Distort Decisions: Information Fidelity in LLM-Compressed Financial Analysis
• Abstract summary: We show that financial compression can alter the investment judgment supported by the original source.<n>In agentic systems, such losses may recur across intermediate steps and amplify throughout the decision process.<n>We propose Agentic Context Compression, which generates multiple candidate compressions and audits their disagreements against the original source.
• Score: 88.39399763902419
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Financial decision-makers face more information than they can directly inspect, making context compression necessary. Yet when large language models (LLMs) compress financial source material, they can alter the investment judgment supported by the original source. We frame this problem as information fidelity: compression loses fidelity when it changes the decision induced by the source. In agentic systems, such losses may recur across intermediate steps and amplify throughout the decision process. Across financial filings and earnings-call transcripts, we find that LLM-based compression can produce fluent and factually plausible compressed contexts that nevertheless alter downstream decisions. We analyze two diagnostic patterns associated with fidelity loss: decontextualization, where salient evidence is retained but separated from the caveats and contextual qualifiers needed for correct interpretation, and model dependency, where different compressors expose different views of the same source. We then propose Agentic Context Compression, which generates multiple candidate compressions and audits their disagreements against the original source. Our results suggest that financial compression should be evaluated not only by efficiency or factuality, but also by its ability to preserve decision-relevant context.

Related papers

• Reading Is Not Using: Retrieval, Judgment, and the Design of AI Financial Research Workflows [7.410179371973137]
  Large language models (LLMs) are increasingly deployed as AI analysts to process financial disclosures.<n>We identify a retrieval-integration gap in long-context financial analysis.<n>We find that a risk disclosure's influence on investment judgments falls to the experimental noise floor.
  arXiv  Detail & Related papers  (2026-08-25T17:31:25Z)
• Diffuse to Compress: Leveraging Diffusion LMs for Lossless Compression [1.133608012542551]
  We study the problem of lossless text compression, motivated by the rapid growth in the collection and storage of digital textual data.<n>We introduce Diffusion Language Models (DLMs) as an alternative inference paradigm to autoregressive LLM-based approaches.
  arXiv  Detail & Related papers  (2026-08-04T08:19:31Z)
• Quantifying the Sources of Instability in LLM-Based Stance Analysis of Public Discourse [4.093009863847175]
  Two distinct sources of instability can arise when preprocessing pipelines produce different outputs from the same input.<n>Using 256 YouTube interviews across 41 public figures from five domains, we compare two speaker-diarization pipelines and two measurement methods.<n>We find that preprocessing pipeline sensitivity is concentrated in speakers with limited video samples.
  arXiv  Detail & Related papers  (2026-07-12T17:15:36Z)
• Lossless Prompt Compression via Dictionary-Encoding and In-Context Learning: Enabling Cost-Effective LLM Analysis of Repetitive Data [0.19780197369405136]
  In this paper, we demonstrate that Large Language Models can learn encoding keys in-context and perform analysis on encoded representations.<n>We present a compression algorithm that identifies repetitive patterns at multiple length scales.<n>This training-free approach works with API-based LLMs, directly addressing fundamental deployment constraints.
  arXiv  Detail & Related papers  (2026-03-19T21:05:53Z)
• Rethinking Soft Compression in Retrieval-Augmented Generation: A Query-Conditioned Selector Perspective [21.41673002861847]
  Retrieval-Augmented Generation (RAG) effectively grounds Large Language Models (LLMs) with external knowledge.<n>Recent research on soft context compression aims to address this by encoding long documents into compact embeddings.<n>We introduce SeleCom, a selector-based soft compression framework for RAG that redefines the encoder's role as query-conditioned information selector.
  arXiv  Detail & Related papers  (2026-01-25T09:06:24Z)
• Decomposed Trust: Exploring Privacy, Adversarial Robustness, Fairness, and Ethics of Low-Rank LLMs [2.1311014724439845]
  We study how low-rank factorization affects trustworthiness across privacy, adversarial robustness, fairness, and ethical alignment.<n>Low-rank compression preserves or improves training data privacy but weakens PII protection during conversation.<n> adversarial robustness is generally preserved and often enhanced, even under deep compression.<n>Ethical reasoning degrades in zero-shot settings but partially recovers with few-shot prompting.
  arXiv  Detail & Related papers  (2025-11-27T04:40:56Z)
• Compression Hacking: A Supplementary Perspective on Informatics Properties of Language Models from Geometric Distortion [56.12939353271623]
  From a geometric standpoint, the word representation space of highly compressed LMs tends to degenerate into a highly anisotropic state.<n>We find this synchronicity is essentially the Compression Hacking'' in LM representations.<n>We propose three refined compression metrics by incorporating geometric distortion analysis and integrate them into a self-evaluation pipeline.
  arXiv  Detail & Related papers  (2025-05-23T12:11:03Z)
• UNComp: Can Matrix Entropy Uncover Sparsity? -- A Compressor Design from an Uncertainty-Aware Perspective [85.08718140718707]
  UNComp is an uncertainty-aware framework that uncovers sparsity patterns that can be used for adaptive compression.<n>By focusing on uncertainty to analyze the sparsity pattern in detail, UNComp reduces the KV cache size to 4.74% of the original, achieves a 6% prefill speedup, and improves throughput by 6.4x.
  arXiv  Detail & Related papers  (2024-10-04T02:32:36Z)
• QUITO-X: A New Perspective on Context Compression from the Information Bottleneck Theory [75.81394991657545]
  We introduce information bottleneck theory (IB) to model the problem.<n>We propose a cross-attention-based approach to approximate mutual information in IB.<n>Our method achieves a 25% increase in compression rate compared to the state-of-the-art.
  arXiv  Detail & Related papers  (2024-08-20T02:44:45Z)
• Beyond Perplexity: Multi-dimensional Safety Evaluation of LLM Compression [33.45167213570976]
  We investigate the impact of model compression on four dimensions: (1) degeneration harm, i.e., bias and toxicity in generation; (2) representational harm, i.e., biases in discriminative tasks; (3) dialect bias; and(4) language modeling and downstream task performance. Our analysis reveals that compression can lead to unexpected consequences.
  arXiv  Detail & Related papers  (2024-07-06T05:56:22Z)
• Breaking the Communication-Privacy-Accuracy Tradeoff with $f$-Differential Privacy [51.11280118806893]
  We consider a federated data analytics problem in which a server coordinates the collaborative data analysis of multiple users with privacy concerns and limited communication capability. We study the local differential privacy guarantees of discrete-valued mechanisms with finite output space through the lens of $f$-differential privacy (DP) More specifically, we advance the existing literature by deriving tight $f$-DP guarantees for a variety of discrete-valued mechanisms.
  arXiv  Detail & Related papers  (2023-02-19T16:58:53Z)
• Learning Scalable $\ell_\infty$-constrained Near-lossless Image Compression via Joint Lossy Image and Residual Compression [118.89112502350177]
  We propose a novel framework for learning $ell_infty$-constrained near-lossless image compression. We derive the probability model of the quantized residual by quantizing the learned probability model of the original residual.
  arXiv  Detail & Related papers  (2021-03-31T11:53:36Z)

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.