Author: Tech Jacks Solutions

From Ranking to Selection: A Simple but Efficient Dynamic Passage Selector for Retrieval Augmented Generationcs.AI updates on arXiv.orgon August 14, 2025 at 4:00 am arXiv:2508.09497v1 Announce Type: cross
Abstract: Retrieval-augmented generation (RAG) systems are often bottlenecked by their reranking modules, which typically score passages independently and select a fixed Top-K size. This approach struggles with complex multi-hop queries that require synthesizing evidence across multiple documents, creating a trade-off where small K values omit crucial information and large K values introduce noise. To address this, we introduce the Dynamic Passage Selector (DPS), a novel reranking framework that treats passage selection as a supervised learning problem. Unlike traditional point-wise or list-wise methods, DPS is fine-tuned to capture inter-passage dependencies and dynamically select the most relevant set of passages for generation. As a seamless plug-and-play module, DPS requires no modifications to the standard RAG pipeline. Comprehensive evaluations on five benchmarks show that DPS consistently outperforms state-of-the-art rerankers and fine-tuning methods. Notably, on the challenging MuSiQue dataset, DPS improves the F1-score by 30.06% and 15.4% over strong baselines like Qwen3-reranker and RankingGPT, respectively. Our results demonstrate that by enabling adaptive evidence selection, DPS substantially enhances reasoning capabilities in complex RAG scenarios.

 arXiv:2508.09497v1 Announce Type: cross
Abstract: Retrieval-augmented generation (RAG) systems are often bottlenecked by their reranking modules, which typically score passages independently and select a fixed Top-K size. This approach struggles with complex multi-hop queries that require synthesizing evidence across multiple documents, creating a trade-off where small K values omit crucial information and large K values introduce noise. To address this, we introduce the Dynamic Passage Selector (DPS), a novel reranking framework that treats passage selection as a supervised learning problem. Unlike traditional point-wise or list-wise methods, DPS is fine-tuned to capture inter-passage dependencies and dynamically select the most relevant set of passages for generation. As a seamless plug-and-play module, DPS requires no modifications to the standard RAG pipeline. Comprehensive evaluations on five benchmarks show that DPS consistently outperforms state-of-the-art rerankers and fine-tuning methods. Notably, on the challenging MuSiQue dataset, DPS improves the F1-score by 30.06% and 15.4% over strong baselines like Qwen3-reranker and RankingGPT, respectively. Our results demonstrate that by enabling adaptive evidence selection, DPS substantially enhances reasoning capabilities in complex RAG scenarios. Read More 

Hallucination vs interpretation: rethinking accuracy and precision in AI-assisted data extraction for knowledge synthesiscs.AI updates on arXiv.orgon August 14, 2025 at 4:00 am arXiv:2508.09458v1 Announce Type: cross
Abstract: Knowledge syntheses (literature reviews) are essential to health professions education (HPE), consolidating findings to advance theory and practice. However, they are labor-intensive, especially during data extraction. Artificial Intelligence (AI)-assisted extraction promises efficiency but raises concerns about accuracy, making it critical to distinguish AI ‘hallucinations’ (fabricated content) from legitimate interpretive differences. We developed an extraction platform using large language models (LLMs) to automate data extraction and compared AI to human responses across 187 publications and 17 extraction questions from a published scoping review. AI-human, human-human, and AI-AI consistencies were measured using interrater reliability (categorical) and thematic similarity ratings (open-ended). Errors were identified by comparing extracted responses to source publications. AI was highly consistent with humans for concrete, explicitly stated questions (e.g., title, aims) and lower for questions requiring subjective interpretation or absent in text (e.g., Kirkpatrick’s outcomes, study rationale). Human-human consistency was not higher than AI-human and showed the same question-dependent variability. Discordant AI-human responses (769/3179 = 24.2%) were mostly due to interpretive differences (18.3%); AI inaccuracies were rare (1.51%), while humans were nearly three times more likely to state inaccuracies (4.37%). Findings suggest AI accuracy depends more on interpretability than hallucination. Repeating AI extraction can identify interpretive complexity or ambiguity, refining processes before human review. AI can be a transparent, trustworthy partner in knowledge synthesis, though caution is needed to preserve critical human insights.

 arXiv:2508.09458v1 Announce Type: cross
Abstract: Knowledge syntheses (literature reviews) are essential to health professions education (HPE), consolidating findings to advance theory and practice. However, they are labor-intensive, especially during data extraction. Artificial Intelligence (AI)-assisted extraction promises efficiency but raises concerns about accuracy, making it critical to distinguish AI ‘hallucinations’ (fabricated content) from legitimate interpretive differences. We developed an extraction platform using large language models (LLMs) to automate data extraction and compared AI to human responses across 187 publications and 17 extraction questions from a published scoping review. AI-human, human-human, and AI-AI consistencies were measured using interrater reliability (categorical) and thematic similarity ratings (open-ended). Errors were identified by comparing extracted responses to source publications. AI was highly consistent with humans for concrete, explicitly stated questions (e.g., title, aims) and lower for questions requiring subjective interpretation or absent in text (e.g., Kirkpatrick’s outcomes, study rationale). Human-human consistency was not higher than AI-human and showed the same question-dependent variability. Discordant AI-human responses (769/3179 = 24.2%) were mostly due to interpretive differences (18.3%); AI inaccuracies were rare (1.51%), while humans were nearly three times more likely to state inaccuracies (4.37%). Findings suggest AI accuracy depends more on interpretability than hallucination. Repeating AI extraction can identify interpretive complexity or ambiguity, refining processes before human review. AI can be a transparent, trustworthy partner in knowledge synthesis, though caution is needed to preserve critical human insights. Read More 

Your Coding Intent is Secretly in the Context and You Should Deliberately Infer It Before Completioncs.AI updates on arXiv.orgon August 14, 2025 at 4:00 am arXiv:2508.09537v1 Announce Type: cross
Abstract: Large Language Models (LLMs) are increasingly used for function completion in repository-scale codebases. Prior studies demonstrate that when explicit instructions–such as docstrings–are provided, these models can generate highly accurate implementations. However, in real-world repositories, such annotations are frequently absent, and performance drops substantially without them. To address this gap, we frame the task as a three-stage process. The first stage focuses on intent inference, where the model analyzes the code preceding the target function to uncover cues about the desired functionality. Such preceding context often encodes subtle but critical information, and we design a reasoning-based prompting framework to guide the LLM through step-by-step extraction and synthesis of these signals before any code is generated. The second stage introduces an optional interactive refinement mechanism to handle cases where preceding context alone is insufficient for intent recovery. In this stage, the model proposes a small set of candidate intentions, enabling the developer to select or edit them so that the inferred intent closely matches the actual requirement. Finally, in the third stage, the LLM generates the target function conditioned on the finalized intent. To support this pipeline, we curate a dataset of 40,000 examples annotated with intermediate reasoning traces and corresponding docstrings. Extensive experiments on DevEval and ComplexCodeEval show that our approach consistently boosts multiple LLMs, achieving over 20% relative gains in both reference-based and execution-based metrics, with the interactive refinement stage delivering additional improvements beyond these gains.

 arXiv:2508.09537v1 Announce Type: cross
Abstract: Large Language Models (LLMs) are increasingly used for function completion in repository-scale codebases. Prior studies demonstrate that when explicit instructions–such as docstrings–are provided, these models can generate highly accurate implementations. However, in real-world repositories, such annotations are frequently absent, and performance drops substantially without them. To address this gap, we frame the task as a three-stage process. The first stage focuses on intent inference, where the model analyzes the code preceding the target function to uncover cues about the desired functionality. Such preceding context often encodes subtle but critical information, and we design a reasoning-based prompting framework to guide the LLM through step-by-step extraction and synthesis of these signals before any code is generated. The second stage introduces an optional interactive refinement mechanism to handle cases where preceding context alone is insufficient for intent recovery. In this stage, the model proposes a small set of candidate intentions, enabling the developer to select or edit them so that the inferred intent closely matches the actual requirement. Finally, in the third stage, the LLM generates the target function conditioned on the finalized intent. To support this pipeline, we curate a dataset of 40,000 examples annotated with intermediate reasoning traces and corresponding docstrings. Extensive experiments on DevEval and ComplexCodeEval show that our approach consistently boosts multiple LLMs, achieving over 20% relative gains in both reference-based and execution-based metrics, with the interactive refinement stage delivering additional improvements beyond these gains. Read More 

DeepSeek reverts to Nvidia for R2 model after Huawei AI chip failsAI Newson August 14, 2025 at 4:04 pm DeepSeek’s plan to train its new AI model, R2, on Huawei’s Ascend chips has failed and forced a retreat to Nvidia while delaying launch. For months, the narrative pushed by Beijing has been one of unstoppable technological progress and a march towards self-sufficiency. However, reality has a habit of biting back. The recent troubles of
The post DeepSeek reverts to Nvidia for R2 model after Huawei AI chip fails appeared first on AI News.

 DeepSeek’s plan to train its new AI model, R2, on Huawei’s Ascend chips has failed and forced a retreat to Nvidia while delaying launch. For months, the narrative pushed by Beijing has been one of unstoppable technological progress and a march towards self-sufficiency. However, reality has a habit of biting back. The recent troubles of
The post DeepSeek reverts to Nvidia for R2 model after Huawei AI chip fails appeared first on AI News. Read More 

Do Biased Models Have Biased Thoughts?cs.AI updates on arXiv.orgon August 13, 2025 at 4:00 am arXiv:2508.06671v2 Announce Type: replace-cross
Abstract: The impressive performance of language models is undeniable. However, the presence of biases based on gender, race, socio-economic status, physical appearance, and sexual orientation makes the deployment of language models challenging. This paper studies the effect of chain-of-thought prompting, a recent approach that studies the steps followed by the model before it responds, on fairness. More specifically, we ask the following question: $textit{Do biased models have biased thoughts}$? To answer our question, we conduct experiments on $5$ popular large language models using fairness metrics to quantify $11$ different biases in the model’s thoughts and output. Our results show that the bias in the thinking steps is not highly correlated with the output bias (less than $0.6$ correlation with a $p$-value smaller than $0.001$ in most cases). In other words, unlike human beings, the tested models with biased decisions do not always possess biased thoughts.

 arXiv:2508.06671v2 Announce Type: replace-cross
Abstract: The impressive performance of language models is undeniable. However, the presence of biases based on gender, race, socio-economic status, physical appearance, and sexual orientation makes the deployment of language models challenging. This paper studies the effect of chain-of-thought prompting, a recent approach that studies the steps followed by the model before it responds, on fairness. More specifically, we ask the following question: $textit{Do biased models have biased thoughts}$? To answer our question, we conduct experiments on $5$ popular large language models using fairness metrics to quantify $11$ different biases in the model’s thoughts and output. Our results show that the bias in the thinking steps is not highly correlated with the output bias (less than $0.6$ correlation with a $p$-value smaller than $0.001$ in most cases). In other words, unlike human beings, the tested models with biased decisions do not always possess biased thoughts. Read More 

How We Reduced LLM Costs by 90% with 5 Lines of CodeTowards Data Scienceon August 21, 2025 at 7:08 pm When clean code hides inefficiencies: what we learned from fixing a few lines of code and saving 90% in LLM cost.
The post How We Reduced LLM Costs by 90% with 5 Lines of Code appeared first on Towards Data Science.

 When clean code hides inefficiencies: what we learned from fixing a few lines of code and saving 90% in LLM cost.
The post How We Reduced LLM Costs by 90% with 5 Lines of Code appeared first on Towards Data Science. Read More