HistLens: Mapping Idea Change across Concepts and Corpora

Yi Jing; Weiyun Qiu; Yihang Peng; Zhifang Sui

cs.CLApr 13, 2026

HistLens: Mapping Idea Change across Concepts and Corpora

Authors: Yi Jing, Weiyun Qiu, Yihang Peng, Zhifang Sui

Organizations: Department of Computer Science and Technology, Tsinghua University, China · State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University, China · School of History, Nanjing University, China · Department of Chinese Language and Literature, Tsinghua University, China

Abstract

Language change both reflects and shapes social processes, and the semantic evolution of foundational concepts provides a measurable trace of historical and social transformation. Despite recent advances in diachronic semantics and discourse analysis, existing computational approaches often (i) concentrate on a single concept or a single corpus, making findings difficult to compare across heterogeneous sources, and (ii) remain confined to surface lexical evidence, offering insufficient computational and interpretive granularity when concepts are expressed implicitly. We propose HistLens, a unified, SAE-based framework for multi-concept, multi-corpus conceptual-history analysis. The framework decomposes concept representations into interpretable features and tracks their activation dynamics over time and across sources, yielding comparable conceptual trajectories within a shared coordinate system. Experiments on long-span press corpora show that HistLens supports cross-concept, cross-corpus computation of patterns of idea evolution and enables implicit concept computation. By bridging conceptual modeling with interpretive needs, HistLens broadens the analytical perspectives and methodological repertoire available to social science and the humanities for diachronic text analysis.

Figures & tables

Figure 1: In New Youth , individual is not unitary but decomposes into sub-semantics such as independent subjecthood , individualism as discourse , and property rights/economic individuality , each with a partly independent trajectory over 1915–1926. HistLens identifies such internal conceptual heterogeneity and diachronic reconfiguration.

Figure 2: Framework overview . We encode diachronic texts with an LLM and project hidden states into sparse SAE activations to obtain interpretable semantic base vectors, forming a shared semantic space. We then perform diachronic modeling in this space to quantify concept dynamics (e.g., peak windows, turning points, and structural shifts) for single-concept and multi-concept/multi-corpus settings, and further distinguish implicit concept signals from explicit lexical mentions, offering new insights for the study of intellectual and conceptual evolution.

Concept	$\bm{\bar{r}}$	$\bm{H}$	Peak	Turn (year, $I$ )
New Youth
individual	0.920	0.741	1920	(1918, $+0.226$ )
nation	0.921	0.743	1924	(1918, $+0.116$ )
society	0.595	0.368	1922	(1918, $-0.213$ )
world	0.900	0.683	1926	(1918, $+0.230$ )
The Guide

Table 1: A slice of the Concept–Corpus Atlas. We report ratio-based and structural signals only: de-lexicalization strength

\bar{r}

, diversity

H

(normalized entropy over orientations), and diachronic anchors (Peak year and the strongest turning point). Turn intensity

I

is signed:

I>0

indicates an upward shift and

I<0

a downward shift at the turning year.

Figure 3: Single-concept decomposition for individual in New Youth . Top: mean activation trajectories of selected SAE base vectors across years, with dashed markers indicating salient transition windows. Bottom: year-to-year relative change rates for the same base vectors, highlighting localized surges and reversals that serve as navigational anchors for close reading.

Figure 4: Multi-concept dynamics in a shared SAE space. Top: for individual , society , nation , and world , we track a small set of salient sparse features and plot their mean activations by year, enabling direct comparison in the same semantic coordinate system. Bottom: window-level composition shifts are summarized as difference heatmaps of feature-share changes across two contrasts, $1917$ – $1919$ relative to pre 1917 and $1922$ – $1924$ relative to $1917$ – $1919$ , revealing coordinated within-concept reweighting around historical junctures.

Figure 5: Cross-corpus decomposition of effective Top- $30$ drifting bases in a shared SAE space. For each concept, we partition the drifting bases into New Youth -only, shared ( New Youth $\cap$ The Guide ), and The Guide -only components, visualizing how cross-corpus overlap versus corpus-specific components vary across concepts.

Figure 6: Explicit vs. implicit concept computation for individual in New Youth . Yearly mean activations are shown for Individualism as Discourse and Property and Economic Individuality in anchor-present (Explicit) and anchor-absent (Implicit) contexts. Vertical dashed lines indicate salient transition windows.

Concept	Layer	Peak	Turn	Avg. Jaccard
individual	06	1923	1918	0.50
	14	1923	1918	0.42
	22	1920	1918	0.48
	29	1920	1918	0.33
nation	06	1924	1918	0.57
	14	1924	1918	0.53

Table 2: Cross-layer robustness results on New Youth . “Avg. 2-gram Jaccard” is the mean 2-gram Jaccard similarity between the evidence-context fingerprint of a given layer and those of the other three layers.

Appendix figures & tables4 assets

Supplementary material from the paper’s appendix.

Appendix

Concept	Cases	Consistency	Selected base	Base rate
society	20	90%	Base 96661 ( Party Linkage and Organizational Alignment )	100%
nation	20	100%	Base 202680 ( Nation-State as Strategic Instrument )	100%
world	20	100%	Base 81379 ( Revolutionary International Field )	100%
individual	20	75%	Base 173164 ( Individualism as Discourse )	100%

Appendix

Table 3: Historian validation summary for sampled implicit cases. Each concept is evaluated on

20

annotated anchor-absent sentences. Concept-level rates are computed from the binary judgments in the annotated validation set; the final column reports the within-base rate for the representative base selected for detailed illustration below.

Corpus	Concept	Strongest Turn (year, $I$ )	Reference Turning Year	Source	$\|\Delta\|$	Acc@ $\pm 1$
New Youth	individual	1918 ( $+0.2260$ )	1919	Uberoi, 1972 ; Ni,2021	1	1
New Youth	nation	1918 ( $+0.1160$ )	1919	Uberoi, 1972 ; Ni,2021	1	1
New Youth	society	1918 ( $-0.2130$ )	1919	Uberoi, 1972 ; Ni,2021	1	1
New Youth	world	1918 ( $+0.2300$ )	1919	Uberoi, 1972 ; Ni,2021	1	1
The Guide	individual	1923 ( $+0.0665$ )	1923	Wilbur, 1984 ; Chen and Wei,2005	0	1
The Guide	nation	1923 ( $-0.0810$ )	1923	Wilbur, 1984 ; Chen and Wei,2005	0	1

Appendix

Table 4: Validation of strongest turning years against corpus-phase turning points recognized in prior historiography.

Method	Implicit-evidence ratio	Evidence Avg. Jaccard	Turn robustness
SAE (ours)	0.920	0.33–0.50 (across layers)	100%
DTM-lite (online LDA)	0.963	0.140	40%
Static word vectors (PPMI + SVD + Procrustes)	0.092	0.872	100%

Appendix

Table 5: Supplementary comparison on New Youth for the anchor concept individual (个人). SAE reruns vary Layers 06/14/22/29 and use top-

20

evidence sentences per run; DTM-lite (online LDA) and static word vectors (PPMI + SVD + Procrustes) rerun

10

random seeds and also use top-

20

evidence sentences per run.

Main-text label	Constituent base(s)	Concept	One-line gloss
Actorhood	90370	individual	The individual as an agentive subject of initiative, self-direction, responsibility, and public action.
Individualism as Discourse	173164	individual	Individualism as an explicit discursive register of autonomy, freedom, and the limits of state coercion.
Property and Economic Individuality	206475	individual	The individual in relation to contract, production, property, and economic coordination.
Societal Transition and Institutional Design	3810	society	Society as a site of structural reorganization, institutional redesign, and transitional ordering.
Organized Praxis and Labor-Movement Alignment	25413 + 224715	society	Society articulated through labor-movement line struggle, socialist organization, and practical mobilization.
Party Linkage and Organizational Alignment	104017 + 96661 + 63228	society	Society articulated through party coordination, class alignment, and communist organizational linkage.

Appendix

Table 6: Semantic labels used in the main text and their mapping to the underlying SAE base(s).

Semantic Change Detection

Semantic change detection identifies how meanings, concepts, or scene contents differ across time in text, images, and other data.

See all 63 papers

Computational conceptual history of scientific concepts: From early digital methods to LLMs
Jun 2, 2026Michael Zichert, Arno SimonsDistributional Semantics Semantic Change Detection
ChronoLens: Measuring Language Change Across Time, Languages, and Linguistic Levels
Aug 4, 2026Gagan Bhatia, Julian Schlenker, Simone Paolo Ponzetto +1Cross-Lingual Representation Alignment Semantic Change Detection
University of Technology Nuremberg · University of Mannheim
Methods, Data, and Conceptual Change: Reflections from Two Quantitative Diachronic Case Studies
May 3, 2026Catherine Wong, Bach Phan-Tat, Susan FitzmauriceSemantic Change Detection
School of History, Philosophy and Digital Humanities, University of Sheffield, Sheffield, United Kingdom · Department of Linguistics, KU Leuven, Leuven, Belgium · School of English, University of Sheffield, Sheffield, United Kingdom

Jun 2, 2026J/K move · Enter open · S save

Computational conceptual history of scientific concepts: From early digital methods to LLMs

Michael Zichert, Arno Simons

Distributional Semantics Semantic Change Detection

Open paper AskPDF arXiv

This article situates large language models (LLMs) within the longer history of computational approaches to concept analysis in the history, philosophy, and sociology of science (HPSS). We examine what LLMs add to existing methods, how they inherit longstanding problems, and review recent case studies that employ them. In the first part, we reconstruct computational conceptual history before LLMs by bringing together three strands of work: early digital methods in HPSS, distributional approaches from digital history and related research, and lexical semantic change detection. We provide an overview of the main challenges and opportunities, focusing on corpus construction, operationalization and modelling choices, and evaluation and interpretation. In the second part, we turn to the era of LLMs, starting with a short introduction to LLMs before reviewing LLM-based work on lexical semantic change detection and relevant case studies in HPSS. We then revisit the earlier methodological questions, showing how issues of corpus construction, model choice and training data, operationalization trade-offs, and evaluation and interpretation play out in LLM-based workflows.

Abstract

Semantic Change Detection

Explore similar work

Computational conceptual history of scientific concepts: From early digital methods to LLMs

ChronoLens: Measuring Language Change Across Time, Languages, and Linguistic Levels

Methods, Data, and Conceptual Change: Reflections from Two Quantitative Diachronic Case Studies