Context Engineering for Trustworthiness: Rescorla Wagner Steering Under Mixed and Inappropriate Contexts

• URL: http://arxiv.org/abs/2509.04500v1
• Date: Tue, 02 Sep 2025 00:40:34 GMT
• Title: Context Engineering for Trustworthiness: Rescorla Wagner Steering Under Mixed and Inappropriate Contexts
• Authors: Rushi Wang, Jiateng Liu, Cheng Qian, Yifan Shen, Yanzhou Pan, Zhaozhuo Xu, Ahmed Abbasi, Heng Ji, Denghui Zhang,
• Abstract summary: We introduce the Poisoned Context Testbed, pairing queries with real-world contexts containing relevant and inappropriate content.<n>Inspired by associative learning in animals, we adapt the Rescorla-Wagner (RW) model from neuroscience to quantify how competing contextual signals influence LLM outputs.<n>We introduce RW-Steering, a two-stage finetuning-based approach that enables the model to internally identify and ignore inappropriate signals.
• Score: 55.70338710797578
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Incorporating external context can significantly enhance the response quality of Large Language Models (LLMs). However, real-world contexts often mix relevant information with disproportionate inappropriate content, posing reliability risks. How do LLMs process and prioritize mixed context? To study this, we introduce the Poisoned Context Testbed, pairing queries with real-world contexts containing relevant and inappropriate content. Inspired by associative learning in animals, we adapt the Rescorla-Wagner (RW) model from neuroscience to quantify how competing contextual signals influence LLM outputs. Our adapted model reveals a consistent behavioral pattern: LLMs exhibit a strong tendency to incorporate information that is less prevalent in the context. This susceptibility is harmful in real-world settings, where small amounts of inappropriate content can substantially degrade response quality. Empirical evaluations on our testbed further confirm this vulnerability. To tackle this, we introduce RW-Steering, a two-stage finetuning-based approach that enables the model to internally identify and ignore inappropriate signals. Unlike prior methods that rely on extensive supervision across diverse context mixtures, RW-Steering generalizes robustly across varying proportions of inappropriate content. Experiments show that our best fine-tuned model improves response quality by 39.8% and reverses the undesirable behavior curve, establishing RW-Steering as a robust, generalizable context engineering solution for improving LLM safety in real-world use.

Related papers

• When Does Context Help? Error Dynamics of Contextual Information in Large Language Models [64.88201012057822]
  We present a unified theoretical framework for analyzing the effect of arbitrary contextual information in large language models.<n>Our analysis characterizes contextual influence through output error dynamics.<n> Experiments across ICL, retrieval-augmented generation, and memory evolution validate our theory and motivate a principled context selection strategy.
  arXiv  Detail & Related papers  (2026-02-09T05:58:41Z)
• Learning to Extract Context for Context-Aware LLM Inference [60.376872353918394]
  User prompts to large language models (LLMs) are often ambiguous or under-specified.<n> contextual cues shaped by user intentions, prior knowledge, and risk factors influence what constitutes an appropriate response.<n>We propose a framework that extracts and leverages such contextual information from the user prompt itself.
  arXiv  Detail & Related papers  (2025-12-12T19:10:08Z)
• Exposing the Cracks: Vulnerabilities of Retrieval-Augmented LLM-based Machine Translation [40.37732389445079]
  We propose a noise synthesis framework and new metrics to evaluate the robustness of REAL-MT.<n>Our results show that low-resource language pairs, which rely more heavily on retrieved context, degrade more severely under noise.<n>Although LRMs possess enhanced reasoning capabilities, they show no improvement in error correction and are even more susceptible to noise.
  arXiv  Detail & Related papers  (2025-10-01T12:43:55Z)
• Rethinking LLM Parametric Knowledge as Post-retrieval Confidence for Dynamic Retrieval and Reranking [23.1400319714807]
  Large Language Models (LLMs) often generate inaccurate responses (hallucinations) when faced with questions beyond their knowledge scope.<n>Retrieval-Augmented Generation (RAG) addresses this by leveraging external knowledge, but a critical challenge remains: determining whether retrieved contexts effectively enhance the models ability to answer specific queries.<n>This challenge underscores the importance of knowledge boundary awareness, which current methods-relying on discrete labels or limited signals-fail to address adequately.
  arXiv  Detail & Related papers  (2025-09-08T09:37:20Z)
• Conflict-Aware Soft Prompting for Retrieval-Augmented Generation [7.20732238547724]
  Retrieval-augmented generation (RAG) enhances the capabilities of large language models (LLMs) by incorporating external knowledge into their input prompts.<n>RAG often fails to resolve the conflict between incorrect external context and correct parametric knowledge, known as context-memory conflict.<n>We introduce Conflict-Aware REtrieval-Augmented Generation (CARE), consisting of a context assessor and a base LLM.<n>CARE effectively mitigates context-memory conflicts, leading to an average performance gain of 5.0% on QA and fact-checking benchmarks.
  arXiv  Detail & Related papers  (2025-08-21T05:36:29Z)
• Can LLMs Detect Their Confabulations? Estimating Reliability in Uncertainty-Aware Language Models [24.72990207218907]
  Large Language Models (LLMs) are prone to generating fluent but incorrect content, known as confabulation.<n>We investigate how in-context information influences model behavior and whether LLMs can identify their unreliable responses.
  arXiv  Detail & Related papers  (2025-08-11T16:12:36Z)
• RADIANT: Retrieval AugmenteD entIty-context AligNmenT -- Introducing RAG-ability and Entity-Context Divergence [5.066415370344766]
  Retrieval-Augmented Generation (RAG) is a technique to enhance factual accuracy by integrating external knowledge into the generation process.<n>This paper introduces Radiant, a framework that merges RAG with alignment designed to optimize the interplay between retrieved evidence and generated content.
  arXiv  Detail & Related papers  (2025-06-28T21:40:35Z)
• Attributing Response to Context: A Jensen-Shannon Divergence Driven Mechanistic Study of Context Attribution in Retrieval-Augmented Generation [32.30660197797758]
  We introduce a novel Jensen-Shannon Divergence driven method to Attribute Response to Context (ARC-JSD)<n>We demonstrate superior accuracy and significant computational efficiency improvements compared to the previous surrogate-based method.<n>Our mechanistic analysis reveals specific attention heads and multilayer perceptron (MLP) layers responsible for context attribution.
  arXiv  Detail & Related papers  (2025-05-22T09:04:03Z)
• Exploring LLM Reasoning Through Controlled Prompt Variations [0.9217021281095907]
  We evaluate how well state-of-the-art models maintain logical consistency and correctness when confronted with four categories of prompt perturbations.<n>Our experiments, conducted on thirteen open-source and closed-source LLMs, reveal that introducing irrelevant context within the model's context window significantly degrades performance.<n>Certain perturbations inadvertently trigger chain-of-thought-like reasoning behaviors, even without explicit prompting.
  arXiv  Detail & Related papers  (2025-04-02T20:18:50Z)
• On the Loss of Context-awareness in General Instruction Fine-tuning [101.03941308894191]
  We investigate the loss of context awareness after supervised fine-tuning.<n>We find that the performance decline is associated with a bias toward different roles learned during conversational instruction fine-tuning.<n>We propose a metric to identify context-dependent examples from general instruction fine-tuning datasets.
  arXiv  Detail & Related papers  (2024-11-05T00:16:01Z)
• FaithEval: Can Your Language Model Stay Faithful to Context, Even If "The Moon is Made of Marshmallows" [74.7488607599921]
  FaithEval is a benchmark to evaluate the faithfulness of large language models (LLMs) in contextual scenarios.<n>FaithEval comprises 4.9K high-quality problems in total, validated through a rigorous four-stage context construction and validation framework.<n>Our study reveals that even state-of-the-art models often struggle to remain faithful to the given context, and that larger models do not necessarily exhibit improved faithfulness.
  arXiv  Detail & Related papers  (2024-09-30T06:27:53Z)
• SFR-RAG: Towards Contextually Faithful LLMs [57.666165819196486]
  Retrieval Augmented Generation (RAG) is a paradigm that integrates external contextual information with large language models (LLMs) to enhance factual accuracy and relevance. We introduce SFR-RAG, a small LLM that is instruction-textual with an emphasis on context-grounded generation and hallucination. We also present ConBench, a new evaluation framework compiling multiple popular and diverse RAG benchmarks.
  arXiv  Detail & Related papers  (2024-09-16T01:08:18Z)
• LLMs' Reading Comprehension Is Affected by Parametric Knowledge and Struggles with Hypothetical Statements [59.71218039095155]
  Task of reading comprehension (RC) provides a primary means to assess language models' natural language understanding (NLU) capabilities.<n>If the context aligns with the models' internal knowledge, it is hard to discern whether the models' answers stem from context comprehension or from internal information.<n>To address this issue, we suggest to use RC on imaginary data, based on fictitious facts and entities.
  arXiv  Detail & Related papers  (2024-04-09T13:08:56Z)
• Improving the Reliability of Large Language Models by Leveraging Uncertainty-Aware In-Context Learning [76.98542249776257]
  Large-scale language models often face the challenge of "hallucination" We introduce an uncertainty-aware in-context learning framework to empower the model to enhance or reject its output in response to uncertainty.
  arXiv  Detail & Related papers  (2023-10-07T12:06:53Z)

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.