---
title: Anchoring Bias Sensitivity Score (ABSS)
url: https://www.emergentmind.com/topics/anchoring-bias-sensitivity-score-abss
type: topic
---

# Anchoring Bias Sensitivity Score (ABSS)

The Anchoring Bias Sensitivity Score (ABSS) is a quantitative metric designed to assess the degree to which an individual, agent, or model exhibits susceptibility to anchoring bias—the cognitive tendency to over-rely on initial cues or “anchors” when making judgments. ABSS has been operationalized across human behavioral experiments, log-based user-action analyses, and large language model (LLM) evaluations, employing rigorous statistical, probabilistic, and attributional frameworks. It unifies previously fragmented methodologies into a scalar index, permitting robust comparison, risk assessment, and mitigation of anchoring bias across different domains.

## 1. Cognitive and Methodological Foundations

Anchoring bias is characterized as a systematic and predictable deviation from a normative reference (PN1), with deviation patterns that must persistently recur, rather than arise by chance (PN2) [2206.15129, 1911.12275]. In quantifying bias sensitivity, ABSS formalizes (a) the detection of systematic deviations in behavioral responses or model outputs as a function of exogenous anchor values and (b) the consolidation of these deviations into a single per-entity metric following established principles from cognitive psychology and behavioral economics.

For human-centric settings, baseline responses are empirically determined from unanchored (control) groups, anchors are introduced under randomized controlled protocols, and the magnitude of bias is calculated relative to individual or population-level shifts in predictions [1911.12275]. In log-based or model-centric contexts, the “norm” is inferred from aggregate behavior or model outputs absent anchors, and deviation patterns are quantified via statistical modeling, differentiating true susceptibility from spurious fluctuations [2206.15129, 2511.05766].

## 2. Mathematical Formalizations and Core Components

The ABSS is constructed from domain-specific definitions, always adhering to the principle that it must (i) be responsive to systematic shifts induced by anchors and (ii) lie on a normalized or bounded scale.

**In human behavioral tasks**, two standard operationalizations are prominent [1911.12275]:
- *Regression Slope*: For user \(i\), ABSS is the slope \(\beta_{i,1}\) in \(P_{ij} = \beta_{i,0} + \beta_{i,1}A_{ij} + \varepsilon_{ij}\), expressing the linear response of predictions \(P_{ij}\) to anchor values \(A_{ij}\). \(\mathrm{ABSS}_i = \beta_{i,1}\).
- *Normalized Bias*: Relative displacement toward the anchor, \(\alpha_{ij} = (P_{ij}-M_j^0)/(A_{ij}-M_j^0)\), aggregated as \(\mathrm{ABSS}_i = \operatorname{median}_j \alpha_{ij}\).

**For user logs and clickstreams**, the deviation vector \(\delta_{k,i}\) of individual attention weights from a learned norm is modeled across prediction windows, with linear fitting \(\delta_{k,i} = \beta_{k,1}\,i + \beta_{k,2}\,w + \varepsilon_{k,i}\). The score is \(\mathrm{ABSS}_k = -\beta_{k,1}\), where \(i\) is visit position and \(w\) indexes windows. Significance is established via statistical testing on \(\beta_{k,1}\) [2206.15129].

**In LLMs**, ABSS is typically the aggregation of multiple submetrics—measuring behavioral distributional shifts (e.g., in log-probabilities of outputs), attributional contributions (e.g., via Shapley values assigned to anchor fields), and their robustness [2511.05766, 2505.15392]. For price negotiation, ABSS averages normalized objective susceptibility (utility drop) and subjective satisfaction change, both mapped to [0,1] [2508.21137]. In generalized LLM scoring:
- *Behavioral*: \(S_B\) rescales the expected value shift (\(\Delta \mathrm{EV}\)) in output distributions, using e.g., a softmax-weighted mean.
- *Attributional*: \(S_A\) is the sign and scaled magnitude of Shapley-value shifts associated with anchors in prompt fields.
- *Statistical weighting*: \(w(p)\) functions reweight contributions by significance; additional robustness and concordance terms modulate the final score.
- *Combined ABSS*: For prompt variation \(v\), \(\mathrm{ABSS}_v = \rho[S_B\,w(p_\mathrm{log}) + S_A\,w(p_\mathrm{shap})] + \lambda_{\mathrm{conc}}c\) [2511.05766].

## 3. Representative Empirical Frameworks

### Human Behavioral and Decision Tasks

Large-scale studies administer anchoring experiments with random anchor assignment, control conditions, and population stratification. ABSS is computed as either the individual's anchor-response regression slope or as the median shift normalized to the anchor–control gap [1911.12275]. Across 62 real-world forecasting questions, the mean anchoring index \(\mathrm{AI}_j\) is approximately 0.61, and population-level regression yields \(\beta_1 \approx 0.6\), with negligible modulation by engagement, prior accuracy, or gender.

### User Log Analytics

Using Hierarchical Attention Networks (HANs), attention weights over user actions in visits to analytic UIs are interpreted as reflecting information reliance. Personalized models yield per-user deviations from the common attention norm; ABSS is derived from the slope of deviation with respect to visit position, after significance testing. Approximately 79% of users show statistically significant anchoring patterns (\(\mathrm{ABSS}_k > 0\)) [2206.15129].

### Large Language Models

LLM-centric ABSS frameworks [2511.05766, 2505.15392] distinguish: 
- Log-probability distributional shifts between high-anchor and low-anchor prompts, captured in paired differences and softmax-based "expected value" metrics.
- Shapley-value attribution quantifying anchor contribution to answer log-probs across marginal prompt subsets.
- Aggregation over controlled prompt families and anchor pairs, with strict statistical controls and robustness metrics.
- Example ABSS values: high for Gemma-2B (~6.8) and Phi-2 (~6.2), intermediate for GPT-2 (~2.1), and negative for GPT-Neo-125M (~–0.9) [2511.05766]. In semantic/numeric priming tasks, ABSS via averaged A-Index and R-Error ranges from ~60% (small models) to ~22% (reasoning-tuned models) [2505.15392].

### Multi-metric Negotiation Simulations

In LLM-driven price negotiation, ABSS synthesizes:
- Objective susceptibility: the difference in buyer utility between baseline and anchor conditions.
- Subjective susceptibility: mean drop in satisfaction across outcome, self, process, and relationship dimensions, scaled to [0,1].
- Joint ABSS: weighted mean of normalized objective and subjective susceptibilities [2508.21137].

| Context               | ABSS Core Formula                                     | Typical Range/Interpretation                |
|-----------------------|-------------------------------------------------------|---------------------------------------------|
| Human forecasts       | Regression slope (\(\beta_{i,1}\)), normalized bias  | 0: anchor-immune, 1: fully anchored         |
| User logs (HAN)       | \(\mathrm{ABSS}_k = -\beta_{k,1}\)                    | >0: anchoring, 0: neutral, <0: recency      |
| LLMs (joint metrics)  | See above (behavioral + attribution)                  | ~–1 … 7 absolute or [0,1] normalized        |
| Negotiation (multi)   | Mean of normalized utility and satisfaction drops     | 0: robust, 1: maximally susceptible         |

## 4. Statistical Foundations, Controls, and Thresholds

Computation of ABSS requires rigorous statistical safeguards:
- Significance of response shifts is assessed via t-tests, Wilcoxon signed-rank, and sign-flip permutation tests, with weights reflecting confidence [2511.05766, 1911.12275].
- For per-user or per-model ABSS, only statistically significant effects are reported; otherwise, scores are set to zero or flagged as inconclusive [2206.15129].
- All normalization steps—removal of outliers (e.g., median ± 2.5 MAD), adjustment to baseline medians, field-based prompt enumeration—are strictly defined to prevent scale artifacts or spurious detection.

Robustness across window sizes, anchor ranges, and prompt templates is empirically validated: HAN-based user log ABSS produces concordance 0.79–0.94 across window sizes; LLM ABSS is resilient under moderate anchor variation but can show attributional fragility when prompt design changes [2206.15129, 2511.05766].

## 5. Empirical Findings and Model Comparisons

Human experimental ABSS consistently shows strong and pervasive anchoring effects, largely invariant to external covariates (e.g., engagement, gender, prior performance) [1911.12275].

HAN methods reveal that conventional frequency-based metrics are underpowered (~70% inconclusive), while attention-based ABSS yields high detection rates of anchoring or recency in real interaction logs [2206.15129].

In LLM benchmarking, model scale and training regime correlate with ABSS magnitude and coherence. Larger models (Gemma-2B, Phi-2, Llama-2-7B) manifest highly positive ABSS scores, indicating robust, attributionally coherent anchoring effects; smaller models display mixed behavioral/attributional alignment or even negative ABSS. Reasoning-tuned LLMs and explicit "anti–dual-process" prompts can reduce—though not eliminate—ABSS [2511.05766, 2505.15392].

In negotiation simulations, both objective (utility) and subjective (satisfaction) ABSS components are significant under anchoring interventions. Reasoning models show reduced ABSS, and individual-level susceptibility is uncorrelated with Big Five personality dimensions [2508.21137].

## 6. Domain-Specific Construction and Interpretation

ABSS construction is adapted to domain requirements:
- **Human studies**: Baseline responses are directly measured. ABSS reflects either direct regression-derived anchor sensitivity or normalized median bias.
- **User-action logs**: ABSS is based on deviation slopes of personalized attention weights against a global norm, providing individualized detection [2206.15129].
- **LLMs**: ABSS merges behavioral log-prob shifts and attributional causality from anchor tokens, with statistical weighting and concordance checks. In some cases, semantic and numerical priming submetrics are averaged [2511.05766, 2505.15392].
- **Multi-metric (negotiation)**: ABSS is the (possibly weighted) mean of normalized objective and subjective drops under anchoring, extending beyond accuracy to experiential impact [2508.21137].

ABSS values are bounded (e.g., [0,1] or defined by regression limits), fully interpretable, and permit robust cross-system or cross-individual comparison.

## 7. Limitations, Extensions, and Future Directions

The ABSS construct is bounded by several analytical and practical constraints:
- Inference of “norms” is only as strong as the baseline or control data employed; poor controls can miscalibrate sensitivity.
- Noise and small samples particularly affect per-individual or per-user ABSS—regularization or mixed-effects modeling is necessary for stability in sparse contexts [1911.12275].
- Attributional coherence in LLMs may break down under prompt variations or differing anchor regimes, cautioning against simplistic model-to-human analogies [2511.05766].
- Current ABSS methodologies are limited to tasks with well-defined anchors and quantifiable outputs; generalizing to free-form domains remains challenging.
- No direct neuron-level mechanistic analysis accompanies most reported LLM ABSS; all conclusions are at the distributional or attribution level.
- Despite partial mitigation via "reasoning" prompts or model architecture, anchoring bias is never completely eliminated in either humans or LLMs [2505.15392, 2508.21137].

Future research targets include applying ABSS to other cognitive biases (framing, availability), integrating log-prob attributions with circuit-level interpretability, and building comprehensive cognitive-bias atlases for both human and machine reasoning [2511.05766, 2505.15392].

Source: https://www.emergentmind.com/topics/anchoring-bias-sensitivity-score-abss