Causal Interventions in Language Models

Follow this topic Ask about this topic

Momentum

55 papers in the last four weeks, up 162% on the four weeks before. 0.5% of all new papers.

Jul 13Week of Sep 28

Latest papers 317

Jun 4, 2026cs.PL

CASS-RTL: Correctness-Aware Subspace Steering for RTL Generation with LLMs

Recent advances in large language models (LLMs) have enabled the automatic synthesis (generation) of register-transfer level (RTL) code from natural language instructions, offering a promising pathway to accelerate chip design. Unlike typical natural language (and software coding) tasks, LLM-based RTL code generation demands strict cycle accuracy with concurrency, where minor logical errors can render a circuit unusable or insecure. While prior work has explored hallucination mitigation via external verification, self-evaluation prompts, retrieval-augmented prompting, domain specific fine-tuning, agentic solutions, and reasoning, these approaches largely overlook the attention-oriented internal mechanisms of LLMs that may inherently correlate with RTL correctness. This work proposes CASS-RTL, a first-of-its-kind framework for discovering and leveraging LLMs' correctness-aware components to guide RTL generation toward functionally accurate outputs. We (i) identify attention heads whose activation patterns consistently differentiate correct from incorrect RTL; (ii) construct a low-dimensional subspace capturing correctness-relevant signals; and (iii) design a lightweight, geometry-aware intervention that steers the model at inference time. CASS-RTL is fully model-agnostic, requires no additional supervision or retraining, and readily integrates into existing models. Empirically, we evaluate CASS-RTL on multiple models and observe 10%-20% improvement in pass@1/5/10 accuracy on VerilogEval and 5% improvement on CVDP, demonstrating the effectiveness of our method in enhancing reliability without sacrificing model efficiency or requiring a large labeled dataset for fine-tuning.

Mohammad Akyash, Nowfel Mashnoor, Kimia Azar +1

Department of Electrical and Computer Engineering (ECE), University of Central Florida, Orlando, FL 32816, USA

Code Generation LLM-Based Program Synthesis RTL Code Generation Causal Interventions in Language Models LLM Code Generation

Jun 4, 2026cs.AI

Answer Presence Drives RAG Rewriting Gains

Retrieval-augmented QA pipelines often route retrieved passages through an LLM \emph{rewriter} before a smaller reader, lifting F1 by tens of points on multi-hop benchmarks; this gain is typically credited to improved evidence quality. We ask whether that lift is causally driven by the gold answer string appearing in the rewritten context rather than by curation per se, using a controlled intervention audit. For each rewritten context we re-run the reader after one of four controlled edits to the compile output: removing the gold answer span, replacing a length-matched random non-answer span (placebo), or injecting the gold into rewrites where it was absent (at the prefix or at a midpoint sentence boundary). Across twelve completed (cell, baseline) intervention runs spanning three reader families (Qwen2.5-7B, Qwen3.5-35B, GLM-4.7), two datasets (HotpotQA, 2WikiMultihopQA), and three compiler arrangements (MA-only, MB-only, MA

+

verify), removing the gold answer drops reader F1 by

28

to

64

points beyond the length-matched placebo on paired \texttt{answer-in-compile} strata, and prepending the gold into rewrites that lacked it raises F1 by

+0.7

to

+9.7

points in

10

of

12

(cell, baseline) combinations. A companion five-sentinel audit shows the conventional single-\texttt{[MASK]} probe is itself sentinel-fragile: on 2Wiki it reports a

+4.12

~F1 ``non-leakage residual'' that flips to

-3.33

to

-7.81

~F1 under four alternative sentinels and fails an equivalence test for three of those four (

1/4

~pass). We do not propose a new rewriter or mitigation; we release the intervention runner and the sentinel panel so that other rewriter-gain claims can be tested against the same standard.

Yuejie Li, Yueying Hua, Ke Yang +8

Ant Group

Multi-Hop QA RAG Security RAG Evaluation Causal Interventions in Language Models

Jun 3, 2026cs.LG

Pattern Selectivity is Not Task-Causal Structure: A Cross-Architecture Mechanistic Study of Composed-Task Circuits in 1B-Class Language Models

We test whether a single screen-and-ablate recipe -- identify attention-head circuits by task-pattern selectivity, then verify by causal ablation against a matched-random null -- produces consistent mechanistic claims across model families. The recipe ports across pipelines; the specific circuit it identifies does not. Across four composed tasks (indirect-object identification, greater-than, successor sequences, variable binding) and three 1B-class language models from distinct training pipelines (Pythia 1B / Pile / dense; OLMo 1B / DCLM / dense; OLMoE 1B-7B / DCLM / mixture-of-experts), we run a unified protocol with the matched-random null sampled across ten seeds per cell. The resulting 12 (task, model) cells contain no two that share the same primary causal screen at comparable effect size: the same task, with the same behavioral capability, is implemented through different attention-pattern types across models. We introduce a five-category screen-outcome taxonomy -- primary cause, secondary cause, correlate, interferer, null -- with quantitative thresholds, and show that all five outcomes appear in the panel. We propose a falsifiable hypothesis: the MoE model in our panel builds composed-task circuits on top of a foundational previous-token positional substrate (the prev-token-circuit ablation is the strongest causal screen on 3 of 4 tasks for OLMoE 1B-7B), with the IOI exception consistent with IOI being a final-position name-copying task whose structure directly probes a different pattern. The hypothesis comes with explicit predictions for other MoE language models. We frame the methodology honestly: the spectral participation-ratio signal from the companion methodology paper is a general indicator of specialized computation; what makes a finding task-specific is the task-pattern screen plus a per-model causal verification.

Yongzhong Xu

Attention Head Analysis Decoder-Only Language Models LLM Interpretability Circuits in Language Models Causal Interventions in Language Models Language Model Probing

Jun 3, 2026cs.SD

Beyond Text Following: Repairable Arbitration Reversals in Audio-Language Models

Audio-language models (ALMs) often follow text that conflicts with audio, even when the audio evidence is clear. This raises a basic question: is the audio-supported answer unavailable, or is it represented but overridden by the conflicting text? We examine this question using a same-audio counterfactual that keeps the audio fixed, removes only the conflicting text, and measures the resulting shift in model preference. Across five ALMs and four conflict tasks, 64.1% of conflict samples show a sign flip: the same-audio branch prefers the audio-supported answer, whereas the joint branch prefers the text-supported answer. This pattern suggests that the relevant audio evidence is encoded but loses in arbitration. Activation patching further localizes the reversal to answer-position computation, and patching effects closely track output candidate-score differences (Spearman rho=0.93). Using this diagnostic, we propose Gated Audio Counterfactual Logit Correction (GACL), a training-free decoding rule that interpolates between joint and same-audio scores. Under a strict 5 pp faithfulness-drop budget, GACL improves nAUC by 17.8 points over the best contrastive baseline and transfers without retuning to vision-text arbitration (up to +40.5 pp).

Yichen Gao, Yiqun Zhang, Zijing Wang +7

Northeastern University, China · Shanghai Artificial Intelligence Laboratory, China

Audio-Language Model Evaluation Audio Understanding Audio-Language Models Contrastive Decoding Causal Interventions in Language Models

Jun 3, 2026cs.CL

Caliper: Probing Lexical Anchors versus Causal Structure in LLMs

Large language models reach 50 to 70% accuracy on causal reasoning benchmarks such as CLadder, but it is unclear whether this reflects structural reasoning or lexical pattern matching. We introduce Caliper, a controlled perturbation that replaces semantic variable names with placeholder tokens while preserving the causal graph and probabilistic specification of each question. Across nine instruction-tuned LLMs from 3.8B to 671B and three causal reasoning benchmarks, lexical anonymization yields robust accuracy drops of +7.6, +27.0, and +11.1 pp on a local 3.8B-14B set, rising to +29.6 and +18.0 pp on CRASS and e-CARE across nine frontier models spanning the 2024-2026 generations. Of 40 engaged model-by-benchmark cells, 39 show a positive gap, and the gap collapses by 17x on CLadder's pseudoword subset. Structured scaffolding and few-shot in-context learning each narrow the gap, but mainly by lowering P0 accuracy on smaller models rather than recovering P1. Current instruction-tuned LLMs, evaluated zero-shot, show little evidence of structural causal reasoning once lexical anchors are removed.

Zhenyu Yu, Shuigeng Zhou

Fudan University

Causal Reasoning in Language Models Causal Reasoning Causal Interventions in Language Models LLM Reasoning

Jun 2, 2026cs.LG

Calibrating Overconfidence Without Sacrificing Confidence: Probe-Conditioned Head Intervention for LLMs

Large language models often express high confidence in answers that are wrong. Standard calibration remedies typically act globally or at the score level, reducing unwarranted confidence but also risking erosion of warranted confidence on correct answers. We introduce Probe-Conditioned Head Intervention (PCHI), an inference-time method that uses a frozen probe to detect likely wrong-but-confident responses and conditionally rescales downstream attention-head outputs during confidence generation. On Qwen3-4B-Instruct solving OpenMathInstruct problems with a structured binary confidence field, readout-token PCHI converts 82.2% of originally wrong-yes confidence readouts to

\texttt{no}

, while a joint intervention across upstream confidence-template tokens reduces ECE from 21.9% to 9.2% and damages only 5.1% of originally correct-yes readouts. The readout-token effect also appears on Gemma3-4B, though upstream interventions are weaker and more mask-dependent. These results show that verbalized overconfidence can be selectively reduced through conditionally applied internal intervention, partially decoupling the suppression of unwarranted confidence from the loss of warranted confidence.

Ke Li, Chongzhe Zhang, Zifan Zeng +3

Huawei Heisenberg Research Center · EPFL · TU Berlin +1

Confidence Estimation in Language Models Language Model Calibration LLM Reliability LLM Uncertainty Estimation Causal Interventions in Language Models

Jun 2, 2026cs.CL

Expert-Aware Causal Tracing of Factual Recall in Sparse MoE Language Models

Activation patching can identify a mixture-of-experts (MoE) block whose clean output restores a corrupted factual prediction. However, because the block output combines contributions from multiple routed experts, block-level rescue does not establish whether the recovery localizes to an individual expert or depends on the routed expert set. We study this question on single-token COUNTERFACT contrasts by corrupting subject-token embeddings, restoring clean block outputs, and then restoring clean-minus-noised expert updates under fixed routing. In Qwen3-30B-A3B-Base, a discovery sweep selects layer 44, and held-out analysis identifies L44E069 as a recurrent routed contributor with positive specificity over same-layer active experts. Its effect is fact-matched and improves true-token probability and rank, which explains part of the layer rescue. In Mixtral-8x7B-v0.1, the selected recurrent singleton is not specific; matched-size controls instead show specificity of the clean-routed top-2 set. These findings show that successful MoE-block restoration does not necessarily imply localization to a single expert.

Yuetian Lu, Ali Modarressi, Yihong Liu +1

Center for Information and Language Processing (CIS), LMU Munich

Mixture-of-Experts Language Models Sparse Mixture-of-Experts Factual Knowledge in Language Models Mixture-of-Experts Models Causal Interventions in Language Models

Jun 2, 2026cs.CL

Causal Evidence of Stack Representations in Modeling Counter Languages Using Transformers

Formal languages have proven to be effective conduits to understand the inner mechanisms of transformers. Past work has shown that transformers trained on next token prediction over counter languages learn representations consistent with an underlying stack structure. Beyond representational analysis, this paper investigates the causal role of these representations. Linear probes are trained to predict the stack depth at each token from the model's hidden states, and a principal representation direction is extracted from the probe. Ablation of this direction from the model causes sequential accuracy to collapse to near 0%, providing strong empirical evidence that the stack representation is not just learned, but is causally necessary for model performance.

Nishit Singh

Birla Institute of Technology and Science, Pilani

Transformer Interpretability Transformer Language Modeling Causal Interventions in Language Models

Jun 2, 2026cs.AI

A Negative Result on Cross-Model Activation Transfer in a Pythia Multi-Hop Setting

Recent work shows that language models can transmit behavioural traits through hidden signals in generated data during training. We ask whether a different activation-mediated channel is viable: can one language model communicate a useful intermediate reasoning state to another at inference time through a post-hoc linear activation bridge, rather than through a textual or structured-token relay? We test this question in a controlled Pythia-160M to Pythia-410M multi-hop reasoning setting. A linear translation layer learns a strong normalized-space map between sender and receiver hidden states, with normalized cosine similarity near 0.97 across seeds. However, when the translated activations are injected into the receiver at inference time, they do not improve downstream answering. Low-strength additive injection remains near the no-injection baseline, with confidence intervals that cross zero. Replacement-style injection is consistently destructive, and rescaling translated vectors to the receiver hidden-state norm does not rescue performance. The result is therefore a scoped negative result: in this setting, offline representational alignment is not sufficient for useful causal communication inside the receiver.

Peiyan Zhang, Jason Xin

Independent Researcher

Causal Interventions in Language Models Representation Alignment

Jun 2, 2026cs.AI

Decomposing how prompting steers behavior

Prompting steers large language models (LLMs) and vision-language models (VLMs) without weight updates, but it remains unclear how instruction changes reshape internal representations to produce behavior. We introduce a nested geometric decomposition framework that treats prompting as a transformation of the representational geometry of the content following the prompt. For each prompt pair, we align representations of the same stimuli under two prompts using increasingly expressive stimulus-invariant maps: translation, rigid transformation with uniform scaling, sequential axis scaling, affine transformation, and nonlinear transformation. We then causally test each map by replacing a single layer's prompt-A hidden state for held-out stimuli with its mapped counterpart and measuring recovery of prompt-B representational geometry and behavior. Across three LLMs, three VLMs, and six text or image datasets spanning style, emotion, scene content, and number, prompts consistently reshape representations toward the instructed task structure. Cross-validated variance decomposition shows that much prompt-induced activation change is captured by shape-preserving maps, especially translation and rigid transformation with uniform scaling, while tier profiles reveal model- and task-specific routing strategies across layers. Crucially, although translation and rigid tiers already improve behavioral agreement, affine transformation is the first tier to nearly recover target-prompt task geometry and yields corresponding behavioral gains. This suggests that cross-dimensional linear mixing is a key mechanism by which prompts reorganize representations toward instructed task structure. Our framework decomposes prompt-induced representational change into interpretable geometric components and reveals how models route task-relevant structure to produce prompt-driven behavior.

Fan L. Cheng, Nikolaus Kriegeskorte

Columbia University

LLM Prompting LLM Interpretability VLM Interpretability Mechanistic Interpretability Causal Interventions in Language Models Representation Geometry in Language Models

Jun 2, 2026cs.LG

Multi-component Causal Tracing in Large Language Models

Causal tracing systematically intervenes on a large language model's (LLM's) internal representations to uncover and quantify the causal pathways linking specific inputs or computations to specific metrics of interest, quantifying the LLM's behavior. Building on previous single-component or single-layer studies, this paper presents a unified framework for causally tracing multiple components simultaneously. This framework systematically identifies the subsets of components (e.g., attention heads and multi-layer perceptron neurons) most critical to a desired target performance metric (e.g., accuracy and fairness). This is achieved by incorporating flexible interventions applied to a wide range of desired metrics. To address the combinatorial complexity of the multi-component problem, an efficient algorithm is designed that leverages soft interventions and a carefully designed metric transformation, converting the combinatorial search problem into a continuous one that can be solved efficiently under proper constraints, thereby generating proper binary decisions for selecting components. Experimental results demonstrate that the proposed method efficiently identifies subsets of the model's components that have a high impact on the target metric, outperforming existing baseline approaches. Our code is available at https://github.com/ZiruiYan/multi-component-causal-tracing.

Zirui Yan, Dennis Wei, Dmitriy A. Katz +2

Rensselaer Polytechnic Institute · IBM Research

LLM Interpretability Causal Reasoning in Language Models Causal Interventions in Language Models

Jun 2, 2026cs.CL

Hallucinations as Orthogonal Noise: Inference-Time Manifold Alignment via Dynamic Contextual Orthogonalization

Hallucination in Large Language Models (LLMs), characterized by the generation of content inconsistent with contextual facts or logical constraints -- remains a persistent challenge for reliable deployment. In this work, we address this issue through a geometric framework rooted in the linear representation hypothesis. We propose that hallucinations manifest as orthogonal noise relative to the semantic manifold of the residual stream. Specifically, we hypothesize that while attention heads ideally propagate information congruent with the context subspace, hallucinations arise when specific heads introduce components orthogonal to this subspace, disrupting the coherence of the latent representation. Based on this formulation, we introduce Dynamic Contextual Orthogonalization (DCO), an inference-time intervention method. DCO utilizes the input residual stream as a dynamic context anchor to perform orthogonal decomposition on attention head outputs. To distinguish between context-aligned semantic updates and divergent noise, DCO employs a layer-wise Z-score suppression mechanism that selectively attenuates outlier orthogonal components based on statistical distributions. Evaluations on Llama-3-8B and 70B across benchmarks such as XSum, NQ-Swap, and IFEval demonstrate that DCO achieves superior contextual faithfulness compared to state-of-the-art intervention baselines. Furthermore, DCO maintains high performance on knowledge-intensive tasks like TriviaQA and TruthfulQA, effectively mitigating the trade-off between hallucination suppression and parametric knowledge retention often observed in existing methods. Our findings validate the geometric interpretation of hallucinations and establish DCO as a computationally efficient approach for enforcing manifold alignment.Our code is available at https://github.com/Harry-Miral/DCO

Mingkuan Zhao, Wentao Hu, Tianchen Huang +6

Xi’an Jiaotong University · Xingchen AGI Lab, China Telecom AI Technology (Beijing) Co., Ltd. · University of Science and Technology of China +2

LLM Hallucination Mitigation Hallucination in Language Models Causal Interventions in Language Models Activation Steering

Jun 1, 2026q-fin.GN

Auditing Asset-Specific Preferences in Financial Large Language Models: Evidence from Bitcoin Representations and Portfolio Allocation

Large language models now power robo-advisors and trading agents, yet whether they carry built-in biases toward specific assets is largely untested. We ask three questions: do LLMs systematically prefer certain financial instruments; can an internal representation with causal leverage over those preferences be identified; and does that representation affect downstream financial decisions? We develop a three-level audit protocol and apply it to Bitcoin. First, a behavioral audit of nine frontier LLMs shows that Bitcoin's ranking among money-like instruments is frame-dependent: models place it around rank 5 of 8 as "reliable money" but near the top under crisis and autonomous-agent frames, and an attribute-swap experiment shows that rankings track functional properties, not names. Second, we open a model's internals: a search across thousands of sparse-autoencoder features in Gemma 3 identifies a dominant Bitcoin-selective feature. Amplifying it shifts the model toward the asset and suppressing it shifts the model away, even when "Bitcoin" never appears in the prompt. Third, we test financial consequences: amplification raises Bitcoin's portfolio share by 5.2 percentage points while suppression lowers it by 4.6 pp, with amplification reallocating within crypto and suppression cutting total crypto exposure. We characterize this as bounded behavioral leverage (leverage meaning causal influence over outputs, not financial leverage): an identifiable internal feature can be perturbed to move financial choices, but only within measurable limits. The framework links internal representations to external recommendations, validated with random controls and mechanism boundaries. As LLMs become autonomous financial agents, this is a first step toward a behavioral layer for emerging know-your-agent (KYA) standards: knowing what an agent prefers, and how far that preference can be moved.

Wenbin Wu

Cambridge Centre for Alternative Finance, University of Cambridge

LLM Auditing LLM Decision-Making Causal Interventions in Language Models Finance Financial Decision-Making

Jun 1, 2026cs.CL

Resonant Context Anchoring: Decoupling Attention Routing and Signal Gain at Inference Time

Large Language Models (LLMs) frequently exhibit "contextual disregard" when faced with input evidence that conflicts with their internal parametric memory, leading to persistent factual hallucinations. Existing mitigation strategies primarily rely on suppressing specific neuron activations or employing computationally expensive contrastive decoding mechanisms, which often result in increased perplexity or significantly elevated inference latency. To address these limitations, we propose Resonant Context Anchoring (RCA), a lightweight inference-time intervention method grounded in the perspective of residual stream signal dynamics. RCA aims to resolve the signal attenuation of external evidence during its propagation through deep networks. The core mechanism involves the orthogonal decoupling of routing logic and information magnitude within the self-attention module. By utilizing raw pre-softmax attention scores as an instantaneous metric of semantic alignment, we construct a dynamic gain field via non-linear rectification to selectively amplify the norms of value vectors corresponding to context tokens, without altering the attention probability distribution. This mechanism effectively elevates the signal-to-noise ratio (SNR) of input evidence within the residual stream mixture, thereby robustly anchoring the generation trajectory to the truthful context during inference. Extensive experiments on the Llama-3 model series demonstrate that RCA significantly improves contextual faithfulness across multiple factual consistency and strong knowledge-conflict tasks, effectively suppressing parametric hallucinations. Furthermore, results confirm that as a training-free and computationally negligible plug-and-play module, RCA achieves a Pareto improvement in faithfulness and fluency while maintaining the model's general language understanding capabilities.

Mingkuan Zhao, Yide Gao, Wentao Hu +6

Xi’an Jiaotong University · University of Science and Technology of China · Tongji University +1

Contextual Faithfulness Hallucination in Language Models Causal Interventions in Language Models Inference-Time Intervention

Jun 1, 2026cs.CL

Mechanistic Diagnostics of Spatial Lexical Bias in Multimodal Large Language Model Spatial Reasoning

Multimodal large language models (MLLMs) remain unreliable on spatial multiple-choice questions, and their failures are often attributed to poorly attended visual information. We identify a complementary failure mode, spatial lexical bias: a spatial relation word added to the answer options can act as a lexical-semantic distractor that draws the model's decision toward that option. Using nine open-weight MLLMs, we show that this phenomenon is widespread. We then isolate diagnostic cases in which a model answers a binary spatial question correctly yet consistently chooses a newly added third spatial option, which we call binary-stable but ternary-fragile cases. Leveraging mechanistic interpretability tools on these cases, we find that the failure arises on the language side rather than the visual side: visual attention analyses and residual-stream probes show the correct spatial relation remains internally available, while irrelevant-option controls, activation patching, and sparse component interventions trace the bias to specific LLM-side channels and neurons. Accordingly, we show that a lightweight LLM-only DPO update on tiny single-object-pair synthetic data mitigates the bias, lifting four-way robust accuracy by up to 100 points on synthetic data, and by 68.0, 32.6, and 20.1 points on broader evaluation datasets WhatsUp, SpatialMQA-Direct, and VSR.

Chuang Ma, Qianying Liu, Tomoyuki Obuchi +6

Kyoto University · NII LLMC · RIKEN AIP +4

VLM Robustness Visual Spatial Reasoning Multimodal Large Language Models Linguistic Bias in Language Models Causal Interventions in Language Models

May 31, 2026cs.CL

Unlocking the Black Box of Latent Reasoning: An Interpretability-Guided Approach to Intervention

Latent reasoning enables Large Language Models (LLMs) to perform multi-step inference within continuous hidden states, offering efficiency gains over explicit Chain-of-Thought (CoT). However, the opacity of these continuous thought vectors hinders their reliability and controllability. This paper bridges the gap between mechanistic interpretability and actionable control. We first present a systematic analysis using structural, causal, and geometric probes, revealing that latent vectors encode compressed, faithful representations of reasoning steps, with early vectors acting as critical causal hubs. Building on this, we operationalize these interpretability insights into a suite of training-free, decode-time interventions that refine the latent reasoning process by imposing the identified geometric and semantic priors. Extensive experiments across multiple model scales and diverse task domains demonstrate that our approaches consistently improve reasoning accuracy. Our interpretability-guided interventions consistently unlock latent capabilities and improve reasoning accuracy without any parameter updates.

Shuochen Chang, Tong Bai, Xiaofeng Zhang +5

1Shanghai Jiao Tong University · 2Fudan University

LLM Interpretability Causal Interventions in Language Models LLM Reasoning Latent Reasoning

May 31, 2026cs.AI

Relational Intervention During Functional Collapse in Large Language Models: A Lexical-Statistical Ablation and a Structure x Register Factorial

We test whether a relational-style intervention delivered during functional collapse in a small language model produces post-collapse behavior distinguishable from technical feedback, from a lexically-matched scrambled control, and from each of the two pragmatic dimensions in isolation. Using Qwen3.5-4B with a deliberately broken bash tool, we run 300 episodes across six conditions in a matched-pairs design (50 tasks): no intervention (A), technical/impersonal (B), relational/first-person (C), scrambled relational (D), technical/first-person (E), and relational/impersonal (F). E and F form a 2x2 factorial with B and C that dissociates relational structure (acknowledgment, absolution, agency restoration, unconditional acceptance) from sender register (first-person vs. impersonal). We report two main findings. First, an attention-behavior dissociation: attention follows lexical surprise (D > F > C > E > B, all q_FDR < 10^{-10}), with the scrambled message capturing the most attention; yet behaviorally A ~ B ~ D < E ~ F << C. Second, the factorial localizes the C effect: neither relational structure alone (F) nor first-person register alone (E) replicates C's behavioral signature; main effects of both dimensions are individually significant, and the structure x register interaction is significant on persistence (p = 0.046). A third dissociation emerges in emotion probes: F tracks C on 7 of 8 probes despite producing only baseline behavior, indicating that relational structure alone installs a probe-level state that only translates into behavior when paired with first-person register. The model's processing decomposes into three dissociable stages: attention (ordered by lexical surprise), probe-level state (ordered by structure), and behavior (ordered by the conjunction of both).

Franco Santana, Horacio Vico

Universidad de la República (UDELAR), Montevideo, Uruguay · DigitalIA Cloud, Montevideo, Uruguay

Causal Interventions in Language Models

May 30, 2026cs.LG

Refit the Probe: Single-Direction Ablation Is Not a Necessity Test

Probes are routinely paired with an intervention: ablate the direction the probe found, run the model, and read the change in task accuracy, taking a large drop as evidence that the computation depends on what the probe read and a near-zero drop as evidence that it does not. Either inference requires that the ablation have removed the target from the layer. We find that the ablation does not remove what it targets. A probe refitted on the ablated activations recovers its original accuracy in every cell we test, and keeps recovering when the probe's entire row space is deleted rather than a single axis, because the quantity survives in the orthogonal complement. Because a refitted probe recovers, neither a large task drop nor a near-zero one establishes whether the model needed the target, and one probe fit detects this. Replacing the ablation with iterative nullspace projection, scored against random subspaces of matched dimension, reverses the conclusion: representations that looked causally inert carry most of the task. The correction also separates where a variable is most readable from where deleting it does most damage, and those are not the same layer in any pretrained model we study. The erasure is defined by a linear probe family, so removing a nonlinearly encoded quantity remains open.

Yuhang Jiang

Independent Researcher

Transformer Interpretability Linear Probing Causal Interventions in Language Models Concept Erasure

May 29, 2026cs.CL

The Sword, Shield, and Achilles' Heel: Characterizing the Linguistic Inductive Bias of Large Language Models for Spatial Reasoning in Navigation Planning

Large Language Model (LLM)-based navigation systems commonly construct explicit spatial representations (e.g., topological graphs, semantic raster maps) and translate them into textual descriptions as LLMs' inputs. However, the linguistic structures of such text-based spatial representations and the choices of contextual features (e.g., topology, geometry) they contain are often treated as neutral engineering decisions rather than key factors that shape LLMs' behavior. To fill the gap, we propose a dual-interventional framework that disentangles linguistic structures from different contextual cues to evaluate the linguistic inductive bias of LLMs for navigation planning. In the framework, representation intervention varies the linguistic format and the degree of linguistic compression, clarifying when linguistic representations support or inhibit navigation planning. Context intervention, combined with contextual feature combination and conflict probing, explicitly clarifies the preferences and weaknesses of LLMs when processing different contextual cues. Experiments across diverse spatial reasoning tasks and multiple model scales reveal a consistent pattern: topological information is a sturdy shield and the backbone of robust planning; linguistic format is a double-edged sword whose effect depends on model size, task demands, and the compression level; and semantic information is a fatal Achilles' heel -- incorrect semantic cues can systematically derail the planning process. Overall, our study shows that effective text-based spatial representations in LLM-based navigation should preserve topological integrity, calibrate representational compression to model capacity, and ensure semantic correctness, rather than simply adopting a single representation. Our code is publicly available at https://github.com/jonesdong150/LLM-Navigation-Inductive-Bias.

Xudong Zhang, Jian Yang, Shengkai Wang +5

1East China Normal University, China · 2Information Engineering University, China · 3Zhengzhou University, China

Large Language Model-Based Robot Planning Causal Interventions in Language Models Spatial Reasoning

May 29, 2026cs.CL

Neuron-Level Interventions for Gendered and Gender-Neutral Generation in Language Models

Language models (LMs) can produce gendered language and stereotypes even when given neutral prompts. Most prior work on gender bias in LMs primarily examines gender through a binary lens (feminine vs. masculine), with limited attention to gender-neutral forms, such as they/them pronouns or neutrally phrased job titles. How gender-related signals are encoded in the internal representations of LMs remains an open question. In this work, we study gender-specific neurons in LMs across three categories: feminine, masculine, and gender-neutral. We propose a neuron-level intervention method to identify neurons that are strongly tied to each gender category. We then test these neurons through controlled generation, showing that activating or masking gender-related neurons can steer a sentence toward a target gender form while preserving its original meaning. To evaluate the effectiveness of our gender-intervention approach, we curate two datasets with controlled sentences labeled across all three gender categories and validate the data quality through human evaluation. Experiments on two open-source LMs show that gender-specific neurons are not evenly distributed across model layers; instead, they concentrate heavily in the earliest layers with smaller contributions from later layers. Compared to existing methods, our method achieves more precise gender control, with less leakage into non-target gender categories and stable output quality through two evaluation criteria. Overall, our work examines how gender is encoded in LMs and provides a simple yet effective approach toward controlled gender intervention for both neuron intervention evaluation and gender bias mitigation. Code and datasets are available at: https://github.com/zhiwenyou103/Gender-Neuron-Intervention

Zhiwen You, Nafiseh Nikeghbal, Jana Diesner

University of Illinois Urbana-Champaign · Technical University of Munich · Munich Center for Machine Learning

Gender Bias in Language Models LLM Interpretability Controllable Text Generation Causal Interventions in Language Models

May 28, 2026cs.CL

Counterfactual Graph for Multi-Agent LLM Calibration

Multi-agent LLM systems often treat agreement as evidence: when many agents in a panel give the same answer, that answer is assumed to be more reliable. We show that this assumption can fail after agents communicate. Communication can induce correlated failures and false consensus, so the same vote share may reflect reliable agreement in one topology but over-confidence in another. We propose CAGE-CAL, a counterfactual agent-graph calibration framework for multi-agent LLMs. For each query, CAGE-CAL compares an observed post-communication agent graph with a matched counterfactual no-communication graph, capturing both pairwise failure correlations and group-level dependencies. Rather than simply counting how many agents agree, CAGE-CAL estimates the counterfactual shift between observed and no-communication dependence, and calibrates confidence accordingly. Across five benchmarks, CAGE-CAL improves reliability discrimination with competitive ECE, and its calibrated confidence further improves topology selection over the best fixed-topology strategy.

Jiatan Huang, Mingchen Li, Ziming Li +3

University of Connecticut · University of Massachusetts, Amherst

AI Agent Reliability Language Model Calibration Multi-Agent Consensus Causal Interventions in Language Models Multi-Agent Communication LLM Agent Reliability

May 28, 2026cs.CL

Probing the Prompt KV Cache: Where It Becomes Dispensable

Prior KV cache compression schemes empirically demonstrate that the prompt cache is partially redundant during decoding, dropping or summarising entries with little accuracy loss. We ask when and what kind of redundancy: at which layers, after how many decoding steps, and in what form can the prompt span KV cache be replaced without breaking the task. A controlled splice intervention swept over layer cutoff and decoding steps shows this redundancy is about form (chat template scaffolding) rather than content. Replacing the upper layer prompt span KV cache with KV cache from a chat template scaffold whose user content is a neutral filler recovers near clean accuracy, while zeroing the same slots collapses accuracy. The dissociation replicates across the Qwen3, Gemma 3, and Llama 3 families on multiple datasets.

Vinayshekhar Bannihatti Kumar, Manoj Ghuhan Arivazhagan, Disha Makhija +1

AWS AI Labs

KV Caching KV-Cache Management KV-Cache Compression Causal Interventions in Language Models Language Model Probing

May 28, 2026cs.LG

Measuring, Localizing, and Ablating Alignment Signatures in LLMs

Aligned language models often exhibit a recognizable AI-like style, yet its connection to post-training and internal representations remains poorly understood. In this work, we study whether post-training introduces or amplifies AI-like stylistic regularities and whether these regularities have a localized internal signature. To this end, we compare human text, base-model generations, and aligned-model generations under matched human-source prefixes. Aligned generations show lower human-corpus affinity and higher AI-detection rates than base generations, suggesting that post-training shifts generated text away from human-corpus style and toward detector-visible AI-like text. We then introduce PASTA (Post-training Alignment Signature Targeted Ablation), a training-free method that estimates a post-training alignment signature from aligned-base residual contrasts and ablates the corresponding direction during decoding. Across 11 aligned models and 6 AI detectors, PASTA lowers the detection rate for most aligned models; this effect transfers well across detectors and is not reproduced by random directions. Qualitative analysis suggests that PASTA generations remain relevant and coherent while exhibiting greater stylistic variation. Together, these results show that AI-like stylistic effects of post-training can be measured, localized, and causally tested through activation ablation.

Aniket Anand, Janvijay Singh, Zhewei Sun +2

University of Chicago · University of Illinois at Urbana-Champaign · Toyota Technological Institute at Chicago

LLM Alignment AI-Generated Text Detection Language Model Post-Training Causal Interventions in Language Models

May 28, 2026cs.CL

Causal Interventions on Continuous Variables: A Case Study on Verb Bias in Steering Vectors for In-Context Learning

Causal interventions in language model representations have largely targeted discrete features, like grammatical number. However, language models must also make use of features that are graded. We introduce a method for causal intervention on continuous variables: given activation vectors paired with a graded target variable, we localize a low-dimensional direction for that variable and use this direction to edit a vectors toward counterfactual target values. We apply this method to a continuous feature that is well-studied in psycholinguistics, namely verb bias (which reflects which syntactic structures tend to follow a given verb). We show that verb bias is causally represented in steering vectors extracted from large language models: counterfactual edits to verb bias systematically shift downstream structural preferences. Verb bias has also previously been linked to in-context learning; in further analyses, we find that steering vectors encode error signals that could drive the error-driven update behavior seen in in-context learning but that these aspects of the steering vectors are not causally used in downstream production. Overall, these results show causal interventions can be applied to continuous variables, though connecting continuous variables to in-context learning remains a challenge.

Zhenghao Herbert Zhou, R. Thomas McCoy, Robert Frank

Department of Linguistics Yale University New Haven, CT 06511, USA

Language Model Steering Causal Reasoning in Language Models Causal Interventions in Language Models Causal Intervention

May 27, 2026cs.AI

Multi-Adapter Representation Interventions via Energy Calibration

Representation intervention has emerged as a promising paradigm for aligning large language models toward desired behaviors without modifying model weights. Existing methods typically apply a fixed intervention uniformly across all inputs. However, we find that the appropriate intervention direction and strength vary substantially across samples, and such indiscriminate intervention leads to degradation of general capabilities on benign inputs. To address these challenges, we propose Multi-Adapter Representation Interventions via Energy Calibration (MARI). Specifically, we introduce a competitive multi-adapter mechanism in which specialized experts capture non-linear correction patterns and adaptively determine the appropriate intervention direction and strength for different samples. Furthermore, we design an energy-based gating module that leverages internal propagation dynamics to distinguish inputs that are applicable for intervention. Extensive experiments across diverse model families and parameter scales demonstrate that MARI achieves state-of-the-art alignment performance. Our method significantly improves performance on TruthfulQA, BBQ, and safety benchmarks, while maintaining and even improving general capabilities on tasks such as MMLU and ARC. Our code is available at https://github.com/V1centNevwake/MARI.

Manjiang Yu, Hongji Li, Junwei Chen +4

The University of Queensland, Brisbane, Australia · Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates · Institute of Science Tokyo, Tokyo, Japan

LLM Alignment LLM Safety Alignment Causal Interventions in Language Models

May 27, 2026cs.AI

Cultural Binding Heads in Language Models

LLMs often default to equal treatment across cultural groups, even though context warrants differentiation: this is a lack of difference awareness. Using mechanistic interpretability and a factorial design on the N4 cultural appropriation benchmark from Wang et al. (2025), we identify 2-3 mid-layer attention heads per model that contribute causally to cultural binding across eight models (base and instruct versions of four architectures). Cultural binding is the process of associating a cultural item with its related identity. Knockout of the identity-to-item edges on these heads lowers the binding strength by 9-23%. The identified heads transfer from instruct to base models, suggesting that cultural binding is created during pre-training. An

α

-scaling shows a graded dose-response. Moderate amplification steering at generation (

α= 2-3

) increases cultural differentiation accuracy by 1-3 pp while leaving reasoning on culturally neutral questions mostly intact. A knowledge probing task shows that models know 3-6 times more than they act upon, indicating that the bottleneck lies in routing and not knowledge.

Avrile Floro, Luca Benedetto

Institut Polytechnique de Paris · Télécom SudParis, Institut Polytechnique de Paris

LLM Interpretability Cultural Bias in Language Models Cultural Knowledge in Language Models Causal Interventions in Language Models

May 27, 2026cs.AI

From Fact Overwriting to Knowledge Evolution: Causal Editing via On-Policy Self-Distillation

While Knowledge Editing (KE) enables efficient updates, its dominant Static Fact Overwriting paradigm treats LLMs as discrete databases, forcibly injecting isolated facts. Fracturing pre-trained logical topologies, this triggers Epistemic Dissonance -- a pathology where un-evolved legacy priors force the model to explicitly negate the injected update. Idealized interventions reveal that this is an inherent structural flaw rather than mere algorithmic noise, with a zero-distortion proxy yielding a catastrophic 95.6% self-refutation rate. Given the causally driven nature of real-world knowledge, grounding updates in explicit causal narratives effectively collapses this conflict rate to just 6.6%, underscoring the imperative for a paradigm shift toward Causal Editing. To internalize this evolution, we propose CODE (Causal On-policy Distillation for Editing). By coupling causal bootstrapping with asymmetric on-policy distillation, CODE engraves causal transition logic directly into parametric memory. Experiments on LLaMA-3.1 and Qwen-2.5 show CODE drastically suppresses self-refutation to 1.8% while securing robust multi-hop accuracy (up to 83.5%), seamlessly transforming discrete fact injection into coherent knowledge evolution. Code is available at https://github.com/CrashBugger/CODE.

Shuaike Li, Kai Zhang, Xianquan Wang +2

State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China

Knowledge Editing Knowledge Conflicts in Language Models Model Editing Causal Interventions in Language Models

May 27, 2026cs.CL

Framing Matters: Addressing Framing Sensitivity in Decision-Making through Behaviorally-Grounded Value Alignment

Large Language Models (LLMs) are increasingly deployed in high-stakes decision-making settings such as legal reasoning, where consistency under factually equivalent inputs is critical. However, we find that fact-preserved but differently framed inputs can significantly destabilize LLM decisions. To systematically investigate this problem, we introduce Fragile, a large-scale benchmark that isolates fact-preserving semantic framing across three controlled dimensions: value-tinted narration, temporal slice, and narrative vividness. Our experiments reveal a high susceptibility of LLMs to framing, with an average decision flip rate of 28.6%. We find that simple prior prompt-level and activation-level interventions not only fail to suppress framing sensitivity but actively amplify it. We therefore propose Valign, a representation-level method that explicitly targets these framing dimensions by anchoring decisions to a stable value prior, steering hidden states toward the model's value-consistent direction, and projecting out temporal-vividness-sensitive directions from the model's hidden states. Valign consistently reduces framing-induced decision flips, demonstrating that robust mitigation requires directly targeting the internal pathways in which framing operates.

Seojin Hwang, Minju Kim, Junhyuk Choi +2

Chung-Ang University, Seoul, Korea

LLM Alignment Framing Effects in Language Models LLM Decision-Making Causal Interventions in Language Models Language Model Robustness

May 27, 2026cs.CL

Where Does Toxicity Live? Mechanistic Localization and Targeted Suppression in Language Models

Large language models frequently generate toxic, hateful, or harmful content, yet existing mitigation methods rely on costly retraining or output-level filtering with no mechanistic insight into where toxicity originates internally. We introduce Meow2X and TRNE, two complementary retraining-free frameworks that localize toxicity to specific layers and neurons by analyzing activation differentials between toxic and neutral prompts, then suppress them via inference-time scaling or minimal rank-one weight edits -- without any gradient descent. Evaluations across five LMs, two benchmarks, and 90 configurations using dual safety evaluators demonstrate consistent toxicity reduction while preserving language modeling quality. Our analysis reveals that toxicity is disproportionately encoded in early MLP layers, varies across architectures, and is systematically underestimated by single-evaluator setups -- underscoring the need for multi-evaluator safety assessment. By bridging mechanistic interpretability with practical detoxification, our framework offers a principled path toward safer, more transparent language models.

Himanshu Beniwal, Mayank Singh

Indian Institute of Technology Gandhinagar

Language Model Safety Evaluation LLM Interpretability LLM Safety Model Editing Causal Interventions in Language Models

May 27, 2026cs.LG

ReSAE: Residualized Sparse Autoencoders for Multi-Layer Transformer Interventions

Sparse autoencoders are usually trained one layer at a time, even though transformer residual stream activations are strongly coupled across depth. This creates a practical problem for multi-layer interventions: different layerwise dictionaries can spend capacity representing the same carried-forward information, and replacing several layers at once can produce interactions that are not predicted by single-layer behavior. We introduce Residualized Sparse Autoencoders (ReSAEs), which fit an affine map between selected layers and train each later-layer SAE on the unexplained residual rather than on the full activation. Reconstructions are mapped back into the original activation space through the fitted affine chain, so ReSAEs can be evaluated with the same intervention protocols as ordinary SAEs. On Pythia-1.4B and Gemma-2-9B, residualization reduces decoder redundancy and improves sparse probing and targeted perturbation in most tested settings. Despite reconstructing less of the raw activation variance, ReSAEs recover more transformer cross entropy under multi-layer replacement. This gain is clearest under teacher-forcing and at sufficient sparsity online, indicating that ReSAEs preserve the components of the activation most relevant to the model's downstream computation. These results suggest that removing linearly predictable cross-layer structure is a useful default for multi-layer SAE interventions.

Prathyush Poduval, Calvin Yeung, Neel Desai +1

Department of Computer Science University of California, Irvine Irvine, CA 92697 · Georgia Institute of Technology Atlanta, GA 30332

Transformer Interpretability Activation Sparsity Sparse Autoencoders Causal Interventions in Language Models