# Which Knowledge Should LLMs Trust? Uncovering a Generalizable Steering Direction Across Knowledge Conflicts

arXiv: https://arxiv.org/abs/2610.20067 · HTML: https://mlsanity.com/paper/2610.20067/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 44 references that are in the map.
- First posted on arXiv 14 Oct 2026.

## Builds on (most cited first, 29 of 29)

- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [Inference-Time Intervention: Eliciting Truthful Answers from a Language Model](https://mlsanity.com/paper/2306.03341/) (2023)
- [When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories](https://mlsanity.com/paper/2212.10511/) (2022)
- [Steering Llama 2 via Contrastive Activation Addition](https://mlsanity.com/paper/2312.06681/) (2023)
- [Refusal in Language Models Is Mediated by a Single Direction](https://mlsanity.com/paper/2406.11717/) (2024)
- [Steering Language Models With Activation Engineering](https://mlsanity.com/paper/2308.10248/) (2023)
- [Evaluating Very Long-Term Conversational Memory of LLM Agents](https://mlsanity.com/paper/2402.17753/) (2024)
- [The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets](https://mlsanity.com/paper/2310.06824/) (2023)
- [LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory](https://mlsanity.com/paper/2410.10813/) (2024)
- [Dissecting Recall of Factual Associations in Auto-Regressive Language Models](https://mlsanity.com/paper/2304.14767/) (2023)
- [Entity-Based Knowledge Conflicts in Question Answering](https://mlsanity.com/paper/2109.05052/) (2021)
- [Knowledge Conflicts for LLMs: A Survey](https://mlsanity.com/paper/2403.08319/) (2024)
- [Improving Instruction-Following in Language Models through Activation Steering](https://mlsanity.com/paper/2410.12877/) (2024)
- [Analyzing the Generalization and Reliability of Steering Vectors](https://mlsanity.com/paper/2407.12404/) (2024)
- [Cutting Off the Head Ends the Conflict: A Mechanism for Interpreting and Mitigating Knowledge Conflicts in Language Models](https://mlsanity.com/paper/2402.18154/) (2024)
- [Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering](https://mlsanity.com/paper/2410.15999/) (2024)
- [Why So Gullible? Enhancing the Robustness of Retrieval-Augmented Models against Counterfactual Noise](https://mlsanity.com/paper/2305.01579/) (2023)
- [Knowledge Mechanisms in Large Language Models: A Survey and Perspective](https://mlsanity.com/paper/2407.15017/) (2024)
- [Parameters vs. Context: Fine-Grained Control of Knowledge Reliance in Language Models](https://mlsanity.com/paper/2503.15888/) (2025)
- [IRCAN: Mitigating Knowledge Conflicts in LLM Generation via Identifying and Reweighting Context-Aware Neurons](https://mlsanity.com/paper/2406.18406/) (2024)
- [AdaCAD: Adaptively Decoding to Balance Conflicts between Contextual and Parametric Knowledge](https://mlsanity.com/paper/2409.07394/) (2024)
- [Taming Knowledge Conflicts in Language Models](https://mlsanity.com/paper/2503.10996/) (2025)
- [Tradeoffs Between Alignment and Helpfulness in Language Models with Steering Methods](https://mlsanity.com/paper/2401.16332/) (2024)
- [DRAGged into Conflicts: Detecting and Addressing Conflicting Sources in Search-Augmented LLMs](https://mlsanity.com/paper/2506.08500/) (2025)
- [Controllable Context Sensitivity and the Knob Behind It](https://mlsanity.com/paper/2411.07404/) (2024)
- [Analysing the Residual Stream of Language Models Under Knowledge Conflicts](https://mlsanity.com/paper/2410.16090/) (2024)
- [Cross-model Transferability among Large Language Models on the Platonic Representations of Concepts](https://mlsanity.com/paper/2501.02009/) (2025)
- [Continuously Steering LLMs Sensitivity to Contextual Knowledge with Proxy Models](https://mlsanity.com/paper/2508.19720/) (2025)
- [Simulated Adoption: Decoupling Magnitude and Direction in LLM In-Context Conflict Resolution](https://mlsanity.com/paper/2602.04918/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) frequently encounter conflicts between internal parametric knowledge and external contextual knowledge, yet the mechanisms governing this selection remain unclear. We show that the choice between context and parametric knowledge is linearly represented and can be controlled along a single direction in the model's residual stream. We first demonstrate that this direction generalizes across factual-conflict settings, including context formats, knowledge categories, and datasets, while consistently shifting behavior between parametric and contextual answers. We then transfer a direction learned from simple factual conflicts to three more complex task families: RAG, memory, and rule following, where models must acquire information from retrieved documents, interaction histories, or explicit rules. Across four model families and multiple transfer settings, steering consistently improves the use of prompt-provided information over the unsteered model. These results suggest that the direction captures a transferable preference for external knowledge rather than a mechanism specific to factual conflicts.