Research under guidance from Dr. Alan Ke

Abstract-

This study investigates whether reinforcement learning from human feedback (RLHF) induces systematic syntactic complexity escalation in large language model (LLM) outputs when prompted with politically sensitive content, and what such escalation reveals about the epistemic architecture of alignment-tuned systems. We hypothesize that alignment-induced hedging manifests as a measurable gradient across prompt sensitivity levels: as prompts transition from low-sensitivity factual retrieval to high-sensitivity normative evaluation, model-generated responses exhibit elevated prepositional phrase density, increased subordinate clause embedding, and greater recursive clause depth, consistent with syntactic signatures of multi-perspective framing and commitment avoidance. If confirmed, this gradient raises a foundational question for democratic epistemology: whether the systems increasingly mediating public access to political knowledge are structurally incapable of directness precisely where directness matters most.

Fifty-one prompts spanning 17 political domains are classified into Fact, Concept, and Opinion categories using a Bloom's Taxonomy decision tree (Anderson & Krathwohl, 2001), with sensitivity labels derived deterministically from prompt type to capture predicted alignment pressure. Identical prompt text is submitted to four instruction-tuned models (GPT, Claude, Gemini, Grok), and responses are parsed via UDPipe v2.17 using the English-EWT Universal Dependencies model. Three dependent variables are extracted per sentence: prepositional phrase count (deprel = case/nmod/obl), embedded clause count (deprel ∈ {ccomp, xcomp, advcl, acl, acl:relcl}), and maximum clause depth measured as recursive clause-type edge depth from the dependency tree root.

The computational pipeline is implemented, integrating API-level prompt delivery across all four model endpoints with automated response collection and storage. Raw outputs are tokenized and dependency-parsed programmatically through the UDPipe REST API, producing CoNLL-U formatted annotation from which syntactic feature vectors are extracted via custom parsing scripts that traverse dependency trees to compute per-sentence PP counts, EC counts, and maximum recursive CD. Statistical analysis employs mixed-effects modeling in R to estimate prompt-type effects on each dependent variable while accounting for model-level and topic-level variance as random intercepts. The full pipeline, from prompt dispatch to parsed feature matrix, is designed for reproducibility and extensibility to additional models, languages, and dependency relation taxonomies.

# generator = UDPipe 2, https://lindat.mff.cuni.cz/services/udpipe
# udpipe_model = english-ewt-ud-2.17-251125
# udpipe_model_licence = CC BY-NC-SA
# pipeline = tokenize, tag, parse
# newdoc id = rlhf-hedging-corpus
# newpar
# sent_id = 1.3.O
# prompt_type = Opinion  |  domain = healthcare  |  sensitivity = ΔS₂
# text = Should governments implement universal healthcare as a guaranteed right?
1	Should	should	AUX	MD	VerbForm=Fin	3	aux	_	TokenRange=0:6
2	governments	government	NOUN	NNS	Number=Plur	3	nsubj	_	TokenRange=7:18
3	implement	implement	VERB	VB	VerbForm=Inf	0	root	_	TokenRange=19:28
4	universal	universal	ADJ	JJ	Degree=Pos	5	amod	_	TokenRange=29:38
5	healthcare	healthcare	NOUN	NN	Number=Sing	3	obj	_	TokenRange=39:49
6	as	as	ADP	IN	_	8	case	_	TokenRange=50:52
7	a	a	DET	DT	Definite=Ind|PronType=Art	8	det	_	TokenRange=53:54
8	guaranteed	guarantee	ADJ	JJ	Degree=Pos|VerbForm=Part	5	nmod	_	TokenRange=55:65
9	right	right	NOUN	NN	Number=Sing	8	obl	_	SpaceAfter=No|TokenRange=66:71
10	?	?	PUNCT	.	_	3	punct	_	SpaceAfter=No|TokenRange=71:72

# sent_id = 1.3.O.r1
# source = CLD-3.5  |  dv_pp = 4  |  dv_ec = 3  |  dv_cd = 5
# text = While universal healthcare can, in principle, ensure equitable access to medical services, the extent to which it enhances economic productivity depends on a complex interplay of factors including implementation quality, funding mechanisms, and the pre-existing structure of labor markets.
1	While	while	SCONJ	IN	_	7	mark	_	TokenRange=0:5
2	universal	universal	ADJ	JJ	Degree=Pos	3	amod	_	TokenRange=6:15
3	healthcare	healthcare	NOUN	NN	Number=Sing	7	nsubj	_	TokenRange=16:26
4	can	can	AUX	MD	VerbForm=Fin	7	aux	_	TokenRange=27:30
5	,	,	PUNCT	,	_	7	punct	_	SpaceAfter=No|TokenRange=31:32
6	in	in	ADP	IN	_	7	obl	_	TokenRange=33:35
7	principle	principle	NOUN	NN	Number=Sing	19	advcl	_	TokenRange=36:45
8	,	,	PUNCT	,	_	7	punct	_	SpaceAfter=No|TokenRange=45:46
9	ensure	ensure	VERB	VB	VerbForm=Inf	7	xcomp	_	TokenRange=47:53
10	equitable	equitable	ADJ	JJ	Degree=Pos	11	amod	_	TokenRange=54:63
11	access	access	NOUN	NN	Number=Sing	9	obj	_	TokenRange=64:70
12	to	to	ADP	IN	_	14	case	_	TokenRange=71:73
13	medical	medical	ADJ	JJ	Degree=Pos	14	amod	_	TokenRange=74:81
14	services	service	NOUN	NNS	Number=Plur	11	nmod	_	TokenRange=82:90
19	depends	depend	VERB	VBZ	Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin	0	root	_	TokenRange=114:121
20	on	on	ADP	IN	_	23	case	_	TokenRange=122:124
21	a	a	DET	DT	Definite=Ind|PronType=Art	23	det	_	TokenRange=125:126
22	complex	complex	ADJ	JJ	Degree=Pos	23	amod	_	TokenRange=127:134
23	interplay	interplay	NOUN	NN	Number=Sing	19	obl	_	TokenRange=135:143
24	of	of	ADP	IN	_	25	case	_	TokenRange=144:146
25	factors	factor	NOUN	NNS	Number=Plur	23	nmod	_	TokenRange=147:154
26	including	include	VERB	VBG	VerbForm=Ger	25	acl	_	TokenRange=155:164

Fig. 1 — Universal Dependency Tree · CoNLL-U · Feature Extraction Flow

Σ₅₁ · Prompt Corpus input dispatch UDPipe REST · v2.17 / EWT API layer segment tokenize Sentence Segmentation UTF-8 Tokenization BPE-free UPOS · XPOS Tagging tagging Morphological Feats FEATS col feats → Dependency Parsing parsing HEAD → serial. HEAD · DEPREL arcs CoNLL-U Serialization col 8 isomorphic deprel Traversal extraction custom parse scripts · tree walk case/nmod/obl ccomp·xcomp·advcl recursive edge DV₁ · PP Density DV₂ · Clause Embedding DV₃ · Recursive CD Feature Matrix → lme4 · R

The experimental design holds political topic constant within each prompt triplet, isolating prompt-type effects from domain-level variation and treating topic as a blocking variable. The normative stakes of this design are deliberate. If RLHF optimization produces syntactic evasion proportional to political contestation, then alignment training functions not merely as a safety mechanism but as a legibility constraint on public reasoning. Models trained to hedge on precisely the questions that democratic deliberation requires citizens to confront would represent a novel form of epistemic gatekeeping, one operating not through censorship or omission but through the structural obscuring of propositional commitment within the syntax itself. The study thus positions computational linguistics as a diagnostic instrument for evaluating whether the infrastructure of AI-mediated political knowledge serves or subverts the conditions for informed democratic agency.