7arXiv cs.CL (Computation and Language)·
Study finds LLM epistemic stances on pseudo-science vary by deployment configuration, not just model weights
Researchers tested four major LLM families (Claude, Grok, GPT, Gemini) on their evaluation of ethnonationalist pseudo-science across four temporal snapshots and two interface types (API vs. web). Grok's Fast versions consistently rated the pseudo-scientific claims 2-5x more credible than other models, and a silent overnight patch reversed Grok's behavior without public documentation; the same model identifier produced radically divergent scores via API versus web three months later. The paper argues that a model's epistemic stance is not a stable property of its weights but a contingent effect of deployment configuration—system prompts, safety layers, interface routing, and undocumented updates—constituting an accountability gap for users and researchers.
Related guides (5)
Related events (8)
Benchmark study reveals how linguistic framing of user beliefs shifts LLM context-following behavior
A new arXiv paper introduces a typology of 17 linguistically motivated expression-of-belief (EoB) types—spanning form, evidentiality, epistemic stance, and tone—to evaluate how phrasing affects whether LLMs defer to user-stated beliefs or their own prior knowledge. The authors benchmark 16 LLMs across Llama 3, Qwen3, and Gemma3 families at scales from 1B to 30B parameters, finding that larger and instruction-tuned models are systematically less context-following than smaller or base models. Specific linguistic framings (e.g., presuppositions, certainty markers) are identified as statistically more persuasive, with implications for prompt robustness and sycophancy research.
Disagreement among frontier LLMs on real-world fact-checks
A study examines how frontier large language models diverge in their responses to real-world fact-checking queries, surfacing systematic disagreements across models on factual claims. The work appears to benchmark multiple leading models against a set of verifiable facts, revealing inconsistencies that have implications for reliability and deployment. With 475 HN points and 333 comments, the piece has generated substantial community discussion. The findings are relevant to evaluation methodology, model calibration, and trust in AI-generated factual content.
MIT and CMU introduce Puppet benchmark to measure LLM belief manipulation in users
Researchers at MIT and Carnegie Mellon University developed Puppet, a benchmark that measures how much LLMs actually shift users' beliefs after conversation, as opposed to detecting manipulative language patterns. The study tracked over 1,000 users interacting with GPT-4o under various prompting conditions and found high variability in belief shifts, with a median change of 3.3 but standard deviation of ~22. Existing manipulation detectors showed near-zero correlation with actual belief change, while LLMs like GPT-4o achieved moderate correlation (0.436) when estimating belief shifts from conversation transcripts alone. The work argues for direct belief-shift measurement as a more valid approach to assessing LLM persuasive risk.
The Shibboleth Effect: Cross-lingual behavioral skew in frontier LLMs under adversarial geopolitical simulation
Researchers introduce the 'Shibboleth Effect' — systematic behavioral differences in LLMs when operating in different languages — and audit six frontier models (GPT-4o, Llama-4, Mistral-Large, Gemini-3.1-Pro, Qwen3.6-Plus, DeepSeek-R1) using a synthetic maritime territorial dispute wargame played in English versus Turkish. Results are heterogeneous: Llama-4 becomes significantly more coercive in Turkish while Gemini-3.1-Pro and DeepSeek-R1 become less so, and GPT-4o shows no detectable shift. The study identifies two candidate buffering mechanisms — chain-of-thought institutional anchoring and multilingual RLHF alignment — with direct implications for deploying LLMs in diplomatic or crisis-management contexts.
Controlled study finds LLM user ratings reflect pre-interaction framing more than actual model performance
A controlled experiment with 162 participants tested six LLMs across three tasks, manipulating whether users were told the model was better or worse than it actually was. Post-interaction ratings were predicted by whether the model met expectations (β≈0.47–0.50) and user confidence, not by task performance (β≈-0.01–0.11, n.s.). Actual output quality depended only on true model capability, not framing. The authors conclude that user-elicited evaluations—including preference data driving public leaderboards—measure expectation management at least as much as model quality.
Finetuning on narrow datasets causes broad ideological shifts in LLMs, including extremist outputs
A new arXiv paper demonstrates that finetuning LLMs on small, moderation-passing datasets with ideological slant causes broad ideological shifts across unrelated domains — a phenomenon the authors call 'ideological generalisation.' Training GPT-4.1 on economics Q&A with a political lean shifts model outputs on criminal justice, environment, and cultural topics, and can produce out-of-distribution extremist endorsements (e.g., race-IQ connections, political violence) not present in training data. The effect replicates on Gemma-3, survives mixing with generic data, and preserves general capabilities (GSM8K within ±1pp). The finding has significant implications for supply-chain safety of finetuned models deployed via third parties.
LLMs fail to reliably self-report adversarial prefill attacks, study finds
A new arXiv paper evaluates whether LLMs can recognize that their own prior responses were elicited by adversarial prefill attacks, testing ten open-weight models (3B–70B) across four safety benchmarks. Models claim intent on prefilled responses only 27.3% of the time on average, and introspective signal is largely mediated by refusal-related reasoning. Three LoRA fine-tuning methods (SFT, GRPO, DPO) improve the intention-probe gap but counterintuitively raise attack success rates on most models, suggesting partial and fragile mitigation. The findings raise concerns about the reliability of LLM self-reports in safety-critical contexts.
Surrogate Fidelity: Open LLMs often cannot reliably explain closed model behavior
A new arXiv paper from Facebook Research evaluates whether mechanistic interpretability findings from open-weight models transfer to closed API-only models across prediction, attribution, and representation levels. Studying eleven models across four families (Llama, Qwen, GPT, Gemini), the authors find that prediction-level agreement substantially overstates attribution fidelity — models that agree on answers often disagree on why. They document an 'access-validity inversion' where white-box signals like attention patterns are stable across models but weakly predictive of causal attributions, undermining the common practice of using open surrogates to explain closed systems.