Mitigating Content Effects on Reasoning in Language Models through Fine-Grained Activation Steering

• URL: http://arxiv.org/abs/2505.12189v1
• Date: Sun, 18 May 2025 01:34:34 GMT
• Title: Mitigating Content Effects on Reasoning in Language Models through Fine-Grained Activation Steering
• Authors: Marco Valentino, Geonhee Kim, Dhairya Dalal, Zhixue Zhao, André Freitas,
• Abstract summary: Large language models (LLMs) frequently demonstrate reasoning limitations, often conflating content plausibility with logical validity.<n>This can result in biased inferences, where plausible arguments are incorrectly deemed logically valid or vice versa.<n>This paper investigates the problem of mitigating content biases on formal reasoning through activation steering.
• Score: 14.298418197820912
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models (LLMs) frequently demonstrate reasoning limitations, often conflating content plausibility (i.e., material inference) with logical validity (i.e., formal inference). This can result in biased inferences, where plausible arguments are incorrectly deemed logically valid or vice versa. Mitigating this limitation is critical, as it undermines the trustworthiness and generalizability of LLMs in applications that demand rigorous logical consistency. This paper investigates the problem of mitigating content biases on formal reasoning through activation steering. Specifically, we curate a controlled syllogistic reasoning dataset to disentangle formal validity from content plausibility. After localising the layers responsible for formal and material inference, we investigate contrastive activation steering methods for test-time interventions. An extensive empirical analysis on different LLMs reveals that contrastive steering consistently supports linear control over content biases. However, we observe that a static approach is insufficient for improving all the tested models. We then leverage the possibility to control content effects by dynamically determining the value of the steering parameters via fine-grained conditional methods. We found that conditional steering is effective on unresponsive models, achieving up to 15% absolute improvement in formal reasoning accuracy with a newly introduced kNN-based method (K-CAST). Finally, additional experiments reveal that steering for content effects is robust to prompt variations, incurs minimal side effects on language modeling capabilities, and can partially generalize to out-of-distribution reasoning tasks. Practically, this paper demonstrates that activation-level interventions can offer a scalable strategy for enhancing the robustness of LLMs, contributing towards more systematic and unbiased formal reasoning.

Related papers

• AMPS: Adaptive Modality Preference Steering via Functional Entropy [66.69992693275061]
  We introduce an instance-aware diagnostic metric that quantifies each modality's information contribution and reveals sample-specific susceptibility to steering.<n> Experimental results show that our instance-aware steering outperforms conventional steering in modulating modality preference.
  arXiv  Detail & Related papers  (2026-02-13T02:29:06Z)
• Abstract Activation Spaces for Content-Invariant Reasoning in Large Language Models [28.102903742881576]
  We introduce a framework for abstraction-guided reasoning that explicitly separates structural inference from lexical semantics.<n>We show that abstraction-aligned steering reduces content-driven errors and improves validity-sensitive performance.
  arXiv  Detail & Related papers  (2026-02-02T18:48:44Z)
• Pushing the Boundaries of Natural Reasoning: Interleaved Bonus from Formal-Logic Verification [49.506412445511934]
  Large Language Models (LLMs) show remarkable capabilities, yet their next-token prediction creates logical inconsistencies and reward hacking.<n>We introduce a formal logic verification-guided framework that dynamically interleaves formal symbolic verification with the natural language generation process.<n>We operationalize this framework via a novel two-stage training pipeline that synergizes formal logic verification-guided supervised fine-tuning and policy optimization.
  arXiv  Detail & Related papers  (2026-01-30T07:01:25Z)
• Steering Language Models Before They Speak: Logit-Level Interventions [9.055997973281919]
  We propose a training-free inference-time logit intervention for controllable generation.<n>Our results show that statistically grounded logit steering can achieve large, consistent, and multi-task control gains.
  arXiv  Detail & Related papers  (2026-01-16T03:00:33Z)
• Analyzing Reasoning Consistency in Large Multimodal Models under Cross-Modal Conflicts [74.47786985522762]
  We identify a critical failure mode termed textual inertia, where models tend to blindly adhere to the erroneous text while neglecting conflicting visual evidence.<n>We propose the LogicGraph Perturbation Protocol that structurally injects perturbations into the reasoning chains of diverse LMMs.<n>Results reveal that models successfully self-correct in less than 10% of cases and predominantly succumb to blind textual error propagation.
  arXiv  Detail & Related papers  (2026-01-07T16:39:34Z)
• ATLAS: Adaptive Test-Time Latent Steering with External Verifiers for Enhancing LLMs Reasoning [13.073472989807675]
  We propose Adaptive Test-time Latent Steering, called (ATLAS)<n>ATLAS dynamically controls steering decisions at inference time using an external, lightweight latent verifier.<n> Experiments on multiple mathematical reasoning benchmarks show that ATLAS consistently outperforms both vanilla decoding and fixed steering baselines.
  arXiv  Detail & Related papers  (2026-01-06T15:27:24Z)
• Towards Comprehensive Stage-wise Benchmarking of Large Language Models in Fact-Checking [64.97768177044355]
  Large Language Models (LLMs) are increasingly deployed in real-world fact-checking systems.<n>We present FactArena, a fully automated arena-style evaluation framework.<n>Our analyses reveal significant discrepancies between static claim-verification accuracy and end-to-end fact-checking competence.
  arXiv  Detail & Related papers  (2026-01-06T02:51:56Z)
• Fact-Checking with Large Language Models via Probabilistic Certainty and Consistency [7.806516365113592]
  Large language models (LLMs) are increasingly used in applications requiring factual accuracy.<n>While fact-checking can mitigate these errors, existing methods typically retrieve external evidence indiscriminately.<n>We introduce Probabilistic Certainty and Consistency (PCC), a framework that estimates factual confidence.
  arXiv  Detail & Related papers  (2026-01-05T21:57:41Z)
• From "Aha Moments" to Controllable Thinking: Toward Meta-Cognitive Reasoning in Large Reasoning Models via Decoupled Reasoning and Control [11.321315058502215]
  Large Reasoning Models (LRMs) have demonstrated a latent capacity for complex reasoning by spontaneously exhibiting cognitive behaviors such as step-by-step reasoning, reflection, and backtracking, commonly referred to as "Aha Moments"<n>However, such emergent behaviors remain unregulated and uncontrolled, often resulting in overthinking, where the model continues generating redundant reasoning content even after reaching reliable conclusions.<n>Current models are unable to monitor and adaptively manage their reasoning process to determine when to continue, backtrack, or terminate.<n>We propose the Meta-cognitive Reasoning Framework (MERA), which explicitly decouples the thinking process into distinct
  arXiv  Detail & Related papers  (2025-08-06T13:59:17Z)
• KV Cache Steering for Controlling Frozen LLMs [80.50365534625438]
  cache steering is a lightweight method for implicit steering of language models.<n>We apply cache steering to induce chain-of-thought reasoning in small language models.
  arXiv  Detail & Related papers  (2025-07-11T17:59:36Z)
• CTRLS: Chain-of-Thought Reasoning via Latent State-Transition [57.51370433303236]
  Chain-of-thought (CoT) reasoning enables large language models to break down complex problems into interpretable intermediate steps.<n>We introduce groundingS, a framework that formulates CoT reasoning as a Markov decision process (MDP) with latent state transitions.<n>We show improvements in reasoning accuracy, diversity, and exploration efficiency across benchmark reasoning tasks.
  arXiv  Detail & Related papers  (2025-07-10T21:32:18Z)
• CLATTER: Comprehensive Entailment Reasoning for Hallucination Detection [60.98964268961243]
  We propose that guiding models to perform a systematic and comprehensive reasoning process allows models to execute much finer-grained and accurate entailment decisions.<n>We define a 3-step reasoning process, consisting of (i) claim decomposition, (ii) sub-claim attribution and entailment classification, and (iii) aggregated classification, showing that such guided reasoning indeed yields improved hallucination detection.
  arXiv  Detail & Related papers  (2025-06-05T17:02:52Z)
• Beyond Templates: Dynamic Adaptation of Reasoning Demonstrations via Feasibility-Aware Exploration [15.711365331854614]
  We introduce Dynamic Adaptation of Reasoning Trajectories (DART), a novel data adaptation framework.<n>Instead of uniformly imitating expert steps, DART employs a selective imitation strategy guided by step-wise adaptability estimation.<n>We validate DART across multiple reasoning benchmarks and model scales, demonstrating that it significantly improves generalization and data efficiency.
  arXiv  Detail & Related papers  (2025-05-27T04:08:11Z)
• 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)
• Patterns Over Principles: The Fragility of Inductive Reasoning in LLMs under Noisy Observations [43.491353243991284]
  We introduce Robust Rule Induction, a task that evaluates large language models' capability in inferring rules from data fused with noisy examples.<n>We also propose Sample-steered Rule Refinement (SRR), a method enhancing reasoning stability via observation diversification and execution-guided feedback.<n>Our findings challenge LLMs' reasoning, revealing susceptibility to hypothesis drift and pattern overfitting, while providing empirical evidence critical for developing human-like inductive systems.
  arXiv  Detail & Related papers  (2025-02-22T10:03:19Z)
• LogiDynamics: Unraveling the Dynamics of Logical Inference in Large Language Model Reasoning [49.58786377307728]
  This paper adopts an exploratory approach by introducing a controlled evaluation environment for analogical reasoning.<n>We analyze the comparative dynamics of inductive, abductive, and deductive inference pipelines.<n>We investigate advanced paradigms such as hypothesis selection, verification, and refinement, revealing their potential to scale up logical inference.
  arXiv  Detail & Related papers  (2025-02-16T15:54:53Z)
• Fostering Appropriate Reliance on Large Language Models: The Role of Explanations, Sources, and Inconsistencies [66.30619782227173]
  Large language models (LLMs) can produce erroneous responses that sound fluent and convincing.<n>We identify several features of LLM responses that shape users' reliance.<n>We find that explanations increase reliance on both correct and incorrect responses.<n>We observe less reliance on incorrect responses when sources are provided or when explanations exhibit inconsistencies.
  arXiv  Detail & Related papers  (2025-02-12T16:35:41Z)
• FactTest: Factuality Testing in Large Language Models with Finite-Sample and Distribution-Free Guarantees [41.78390564658645]
  Large Language Models (LLMs) to generate hallucinations and non-factual content undermines their reliability in high-stakes domains. We introduce FactTest, a novel framework that statistically assesses whether a LLM can confidently provide correct answers to given questions. We show that FactTest effectively detects hallucinations and improves the model's ability to abstain from answering unknown questions, leading to an over 40% accuracy improvement.
  arXiv  Detail & Related papers  (2024-11-04T20:53:04Z)
• MIRAGE: Evaluating and Explaining Inductive Reasoning Process in Language Models [19.81485079689837]
  We evaluate large language models' capabilities in inductive and deductive stages.<n>We find that the models tend to consistently conduct correct deduction without correct inductive rules.<n>In the inductive reasoning process, the model tends to focus on observed facts that are close to the current test example in feature space.
  arXiv  Detail & Related papers  (2024-10-12T14:12:36Z)
• Sequential Representation Learning via Static-Dynamic Conditional Disentanglement [58.19137637859017]
  This paper explores self-supervised disentangled representation learning within sequential data, focusing on separating time-independent and time-varying factors in videos. We propose a new model that breaks the usual independence assumption between those factors by explicitly accounting for the causal relationship between the static/dynamic variables. Experiments show that the proposed approach outperforms previous complex state-of-the-art techniques in scenarios where the dynamics of a scene are influenced by its content.
  arXiv  Detail & Related papers  (2024-08-10T17:04:39Z)
• A Closer Look at the Self-Verification Abilities of Large Language Models in Logical Reasoning [73.77088902676306]
  We take a closer look at the self-verification abilities of large language models (LLMs) in the context of logical reasoning. Our main findings suggest that existing LLMs could struggle to identify fallacious reasoning steps accurately and may fall short of guaranteeing the validity of self-verification methods.
  arXiv  Detail & Related papers  (2023-11-14T07:13:10Z)

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.