5arXiv cs.CL (Computation and Language)·
Reasoning graphs improve robustness of LLM authorship attribution against obfuscation
A new arXiv paper proposes using graph neural networks over argument-mining-derived reasoning graphs to attribute authorship of LLM-generated text, moving beyond surface-level linguistic features. The approach outperforms a Longformer baseline by up to 27 percentage points under paraphrasing and backtranslation obfuscation attacks, and by 19 points when generalizing to unseen model versions. The work addresses a practical gap in AI-generated text detection: robustness to adversarial rewriting and model version drift.
Related guides (2)
Related events (8)
Detecting LLM-Generated Text Using Classical Machine Learning Methods
A blog post explores using classical machine learning techniques (as opposed to neural approaches) to detect LLM-generated text. The post attracted notable Hacker News engagement with 168 points and 116 comments, suggesting practical interest from the community. LLM-generated text detection is an active area relevant to academic integrity, content moderation, and AI safety.
Instruction tuning plus model merging improves reasoning LMs in verifiable and unverifiable domains
A new arXiv preprint proposes a two-step method for adapting reasoning language models (RLMs) to domains lacking reliable verifiers: first apply standard supervised fine-tuning (without reasoning traces) on the target domain, then merge the resulting model with the original RLM to recover reasoning behavior. The technique is evaluated on both verifiable domains (coding) and hard-to-verify domains (text summarization), showing improvements while preserving general RLM capabilities. Notably, the authors report the full adaptation can be achieved for under $3, making it highly accessible.
Study finds LLM-generated research ideas cluster around synthesis and bridging, diverging from human distribution
A new arXiv paper introduces a large-scale evaluation framework for comparing LLM-generated research ideas against human-authored ones, using reverse-engineered prior-work sets as prompts. The authors develop a two-axis taxonomy of research taste (opportunity pattern and research paradigm) and find a consistent distributional gap: LLMs over-index on bridge-like opportunities and synthesis methods, while human researchers spread more broadly across framing and contribution types. The result suggests current LLMs produce reasonable but systematically narrower and shifted ideation relative to human researchers.
GraphReview: Scientific Paper Evaluation via LLM-Based Graph Message Passing
GraphReview proposes a graph-based LLM framework that models scientific paper evaluation as review-signal message passing over a semantic paper graph, capturing both intrinsic quality and relational context (synchronic and diachronic links). LLMs estimate node-level quality priors and generate edge-level comparative evidence via pairwise comparisons, while Personalized PageRank integrates signals for ranking, decision prediction, and review generation. The system uses reward-induced maximum likelihood objectives to train LLM backbones and achieves average improvements of 29.7% over the strongest baseline on decision and ranking metrics, including 23.7% accuracy gain and 57.6% Spearman's ρ gain.
Theoretical framework for grounding LLM reasoning under incomplete knowledge graph evidence
A new arXiv preprint develops a formal theoretical framework for understanding how LLMs reason when guided by incomplete knowledge graphs. The authors introduce constructs including entity anchors, typed relation residuals, path energies, and support regions, and prove that under open-world incompleteness no hard rule can simultaneously reject all false unsupported trajectories while retaining all true-but-unobserved ones. Soft grounding is characterized as a KL-regularized deformation of the LLM prior, with hard conditioning as an infinite-penalty limit. The framework yields stability bounds under evidence perturbations and has implications for GraphRAG, KGQA, graph agents, constrained decoding, and faithful generation.
Learning to Reason with LLMs
OpenAI announced a new model or capability focused on reasoning in large language models, published on September 12, 2024. The post, hosted on the OpenAI blog, describes advances in training LLMs to perform complex multi-step reasoning. This likely corresponds to the release of the o1 (formerly 'Strawberry') model series, which uses chain-of-thought reasoning trained via reinforcement learning to achieve significantly improved performance on math, science, and coding benchmarks.
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.
Survey chapter on LLM mechanisms, emergent capabilities, and cognition debates
A new arXiv preprint surveys current understanding of large language models, covering the Transformer architecture, emergent capabilities resembling human cognition (symbolic reasoning, theory of mind, deception), and explainability approaches from neuron activation analysis to circuit tracing. The chapter also engages the debate over whether LLMs genuinely understand or merely pattern-match, arguing against reductive anti-anthropomorphism while acknowledging human-LLM differences. It is framed as a book chapter synthesizing recent empirical findings and theoretical positions.