Self-Reflective Generation
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
Self-Reflective Generation at Test Time
arXiv:2510.02919v2 Announce Type: replace Abstract: Large language models (LLMs) increasingly solve complex reasoning tasks via long chain-of-thought, but their forward-only autoregressive generation process is fragile; early token errors can cascade, which creates a clear need for self-reflection mechanisms. However, existing self-reflection either performs revisions over full drafts or learns self-correction via expensive training, both fundamentally reactive and inefficient. To address...
Closing the Prior-Posterior Loop: Self-Reflective Molecular Design with Analysis-Driven LLM Iteration
arXiv:2606.09520v1 Announce Type: new Abstract: Can a general-purpose large language model design molecules with the precision of a seasoned chemist? Current LLM-based frameworks answer this question with scalar feedback loops-generate, score, reject-that amount to informed trial-and-error. Here we show that replacing a single number with the full physicochemical rationale from first-principles calculations transforms the LLM from a stochastic sampler into a causal reasoner.
Closing the Prior-Posterior Loop: Self-Reflective Molecular Design with Analysis-Driven LLM Iteration
arXiv:2606.09520v1 Announce Type: cross Abstract: Can a general-purpose large language model design molecules with the precision of a seasoned chemist? Current LLM-based frameworks answer this question with scalar feedback loops-generate, score, reject-that amount to informed trial-and-error. Here we show that replacing a single number with the full physicochemical rationale from first-principles calculations transforms the LLM from a stochastic sampler into a causal reasoner.
REFLECTOR: Internalizing Step-wise Reflection against Indirect Jailbreak
arXiv:2605.20654v2 Announce Type: replace Abstract: While Large Language Models (LLMs) demonstrate remarkable capabilities, they remain susceptible to sophisticated, multi-step jailbreak attacks that circumvent conventional surface-level safety alignment by exploiting the internal generation process. To address these vulnerabilities, we propose Reflector, a principled two-stage framework that internalizes self-reflection within the generation trajectory. Reflector first leverages...
Agent-Orchestrated Adaptive RAG: A Comparative Study on Structured and Multi-Hop Retrieval
arXiv:2606.05658v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs) by grounding their responses in external knowledge, but conventional pipelines rely on static, single-step retrieval that limits performance on complex queries. This paper presents an Agent-Orchestrated Adaptive RAG framework that introduces dynamic query decomposition, iterative retrieval, and a bounded self-reflective evaluation loop. We evaluate the system across two...
Breaking Dual Bottlenecks: Evolving Unified Multimodal Models into Self-Adaptive Interleaved Visual Reasoners
arXiv:2605.14709v2 Announce Type: replace Abstract: Recent unified models integrate multimodal understanding and generation within a single framework. However, an "understanding-generation gap" persists, where models can capture user intent but often fail to translate this semantic knowledge into precise pixel-level manipulation. This gap results in two bottlenecks in anything-to-image task (X2I): the attention entanglement bottleneck, where blind planning struggles with complex prompts, and...
SSR: Can Simulated Patients Learn to Stigmatize Themselves? Modeling Self-Stigma through Internal Monologue
new Abstract: Simulating patients with large language models (LLMs) is a promising tool for mental health training, but existing approaches fail to capture a key clinical reality: self-stigma. Patients experiencing self-stigma, the internalization of negative stereotypes, often exhibit context-sensitive resistance, such as avoidance, denial, or self-blame, which current models render as static or uniformly compliant behavior. To address this, we introduce a novel simulation framework...
David Sullivan BBC Panorama probe as ex-Page 3 model set to make string of allegations against him
David Sullivan BBC Panorama probe as ex-Page 3 model set to make string of allegations against him David Sullivan has denied any wrongdoing, saying "after a lifetime spent building businesses in the adult industry... it is sadly inevitable that a small number of improper conduct claims are being made against me" An ex-Page 3 model is due to make a string of allegations against former West Ham United owner David Sullivan. The woman - who we are not naming - is due to appear on Panorama...
Obama Writes His Own Story
On a recent morning at Chicago’s new Obama Presidential Center, the institution’s leadership discussed presidential papers the way a decluttering convert might talk about some old sweaters they tossed because they did not spark joy. The campus contains many features sure to delight the misty-eyed visitors who will flock here once it opens, on June 19: a museum that can come across like a pep talk from a more hopeful time; a light-filled basketball court; a whimsical playground; a public...