Skip to content
← Back to explorer

Epistemic Bias Injection: Biasing LLMs via Selective Context Retrieval

Hao Wu, Prateek Saxena · Nov 30, 2025 · Citations: 0

How to use this paper page

Coverage: Stale

Use this page to decide whether the paper is strong enough to influence an eval design. It summarizes the abstract plus available structured metadata. If the signal is thin, use it as background context and compare it against stronger hub pages before making protocol choices.

Best use

Background context only

Metadata: Stale

Trust level

Provisional

Signals: Stale

What still needs checking

Structured extraction is still processing; current fields are metadata-first.

Signal confidence unavailable

Abstract

When answering user queries, LLMs often retrieve knowledge from external sources stored in retrieval-augmented generation (RAG) databases. These are often populated from unvetted sources, e.g. the open web, and can contain maliciously crafted data. This paper studies attacks that can manipulate the context retrieved by LLMs from such RAG databases. Prior work on such context manipulation primarily injects false or toxic content, which can often be detected by fact-checking or linguistic analysis. We reveal a more subtle threat, Epistemic Bias Injection (EBI), in which adversaries inject factually correct yet epistemically biased passages that systematically emphasize one side of a multi-viewpoint issue. Although linguistically coherent and truthful, such adversarial passages effectively crowd out alternative viewpoints and steer model outputs toward an attacker-chosen stance. As a core contribution, we propose a novel characterization of the problem: We give a geometric metric that quantifies epistemic bias. This metric can be computed directly on embeddings of text passages retrieved by the LLM. Leveraging this metric, we construct EBI attacks and develop a lightweight prototype defense called BiasDef for them. We evaluate them both on a comprehensive benchmark constructed from public question answering datasets.Our results show that: (1) the proposed attack induces significant perspective shifts, effectively evading existing retrieval-based sanitization defenses, and (2) BiasDef substantially reduces adversarial retrieval and bias in LLM's answers. Overall, this demonstrates the new threat as well as the ease of employing epistemic bias metrics for filtering in RAG-enabled LLMs.

Use caution before copying this protocol

Use this page for context, then validate protocol choices against stronger HFEPX references before implementation decisions.

  • Structured extraction is still processing; current fields are metadata-first.

HFEPX Relevance Assessment

Signal extraction is still processing. This page currently shows metadata-first guidance until structured protocol fields are ready.

Best use

Background context only

Use if you need

A provisional background reference while structured extraction finishes.

Main weakness

Structured extraction is still processing; current fields are metadata-first.

Trust level

Provisional

Eval-Fit Score

Unavailable

Eval-fit score is unavailable until extraction completes.

Human Feedback Signal

Not explicit in abstract metadata

Evaluation Signal

Weak / implicit signal

HFEPX Fit

Provisional (processing)

Extraction confidence: Provisional

What This Page Found In The Paper

Each field below shows whether the signal looked explicit, partial, or missing in the available metadata. Use this to judge what is safe to trust directly and what still needs full-paper validation.

Human Feedback Types

provisional

Crowd/annotator signal

Confidence: Provisional Best-effort inference

Directly usable for protocol triage.

Evidence snippet: When answering user queries, LLMs often retrieve knowledge from external sources stored in retrieval-augmented generation (RAG) databases.

Evaluation Modes

provisional

Automatic metrics

Confidence: Provisional Best-effort inference

Includes extracted eval setup.

Evidence snippet: When answering user queries, LLMs often retrieve knowledge from external sources stored in retrieval-augmented generation (RAG) databases.

Quality Controls

provisional

Not reported

Confidence: Provisional Best-effort inference

No explicit QC controls found.

Evidence snippet: When answering user queries, LLMs often retrieve knowledge from external sources stored in retrieval-augmented generation (RAG) databases.

Benchmarks / Datasets

provisional

Not extracted

Confidence: Provisional Best-effort inference

No benchmark anchors detected.

Evidence snippet: When answering user queries, LLMs often retrieve knowledge from external sources stored in retrieval-augmented generation (RAG) databases.

Reported Metrics

provisional

Not extracted

Confidence: Provisional Best-effort inference

No metric anchors detected.

Evidence snippet: When answering user queries, LLMs often retrieve knowledge from external sources stored in retrieval-augmented generation (RAG) databases.

Rater Population

provisional

Unknown

Confidence: Provisional Best-effort inference

Rater source not explicitly reported.

Evidence snippet: When answering user queries, LLMs often retrieve knowledge from external sources stored in retrieval-augmented generation (RAG) databases.

Human Data Lens

This page is using abstract-level cues only right now. Treat the signals below as provisional.

  • Potential human-data signal: Crowd/annotator signal
  • Potential benchmark anchors: No benchmark names detected in abstract.
  • Abstract highlights: 3 key sentence(s) extracted below.

Evaluation Lens

Evaluation fields are inferred from the abstract only.

  • Potential evaluation modes: Automatic metrics
  • Potential metric signals: No metric keywords detected.
  • Confidence: Provisional (metadata-only fallback).

Research Brief

Metadata summary

When answering user queries, LLMs often retrieve knowledge from external sources stored in retrieval-augmented generation (RAG) databases.

Based on abstract + metadata only. Check the source paper before making high-confidence protocol decisions.

Key Takeaways

  • When answering user queries, LLMs often retrieve knowledge from external sources stored in retrieval-augmented generation (RAG) databases.
  • These are often populated from unvetted sources, e.g.
  • the open web, and can contain maliciously crafted data.

Researcher Actions

  • Compare this paper against nearby papers in the same arXiv category before using it for protocol decisions.
  • Validate inferred eval signals (Automatic metrics) against the full paper.
  • Use related-paper links to find stronger protocol-specific references.

Caveats

  • Generated from abstract + metadata only; no PDF parsing.
  • Signals below are heuristic and may miss details reported outside the abstract.

Related Papers

Papers are ranked by protocol overlap, extraction signal alignment, and semantic proximity.

No related papers found for this item yet.

Get Started

Join the #1 Platform for AI Training Talent

Where top AI builders and expert AI Trainers connect to build the future of AI.
Self-Service
Post a Job
Post your project and get a shortlist of qualified AI Trainers and Data Labelers. Hire and manage your team in the tools you already use.
Managed Service
For Large Projects
Done-for-You
We recruit, onboard, and manage a dedicated team inside your tools. End-to-end operations for large or complex projects.
For Freelancers
Join as an AI Trainer
Find AI training and data labeling projects across platforms, all in one place. One profile, one application process, more opportunities.