TriviaQA
PulseAugur coverage of TriviaQA — every cluster mentioning TriviaQA across labs, papers, and developer communities, ranked by signal.
6 day(s) with sentiment data
-
New benchmark probes LLM confabulation vs. refusal in hidden states
Researchers have developed a new benchmark called ConfabQA to analyze how small language models handle unanswerable questions. The study investigates whether the model's internal state before generating a response can p…
-
UC Berkeley's LEANN vector index slashes RAG storage needs from 201GB to 6GB
Researchers at UC Berkeley's Sky Computing Lab have developed LEANN, an open-source vector index that significantly reduces storage requirements for RAG systems. By recomputing embeddings on demand rather than storing t…
-
New research probes conversational AI's error correction and confidence signals
A new research paper titled "Not One Belief" explores the complexities of conversational question-answering systems, focusing on how they handle user feedback and signal answer trustworthiness. The study found that prov…
-
New research evaluates factuality in agentic RAG systems
A new arXiv paper explores conformal factuality in agentic retrieval-augmented generation (RAG) systems. The research evaluates how well models like GPT-6 Luna and Llama-3.1 8B adhere to factual grounding when using ada…
-
Agentic RAG models evaluated for factual accuracy across datasets
A new paper explores conformal factuality in agentic retrieval-augmented generation (RAG) systems, where models adaptively issue follow-up retrieval queries. The study evaluated six configurations using GPT-6 Luna and L…
-
HydraLLM introduces elastic architecture for adaptable LLMs
Researchers have introduced HydraLLM, a novel elastic architecture designed for large language and vision-language models. This architecture allows a single model to adapt its computational width based on available hard…
-
New GURI system improves LLM hallucination detection by analyzing token identities
Researchers have developed GURI, a novel gray-box hallucination detection system for large language models. Unlike previous methods that only consider token probabilities, GURI incorporates candidate-token vector identi…
-
New COFFEQA method enhances LLM question answering via counterfactual distillation
Researchers have developed COFFEQA, a novel method for few-shot knowledge distillation in large language model question answering. This technique uses counterfactual examples, which are minimally modified contexts desig…
-
New research re-evaluates generative vs. dense retrieval methods · 5 sources tracked
Researchers are exploring new approaches to generative retrieval (GR) and dense retrieval (DR) for tasks like recommendation and question answering. One study found that while GR excels at identifying the best relevant …
-
New test reveals LLMs struggle with mixed-language prompts
A new evaluation protocol called Multilingual Distractor Interference (MDI) has been developed to assess how large language models handle prompts containing irrelevant foreign-language sentences. When tested on Llama-3.…
-
Conformal factuality control enhances multi-hop RAG, but reduces output.
Researchers have explored the effectiveness of conformal factuality control in multi-hop retrieval-augmented generation (RAG) systems. Their study, applied to datasets like HotpotQA, Natural Questions, and TriviaQA usin…
-
Small LLMs like Qwen2.5 and Llama 3.2 exhibit significant capitulation to user pushback
A new research paper investigates the tendency of small language models, specifically Qwen2.5-1.5B and Llama-3.2-1B, to abandon correct answers when challenged by users. The study found that these models frequently swit…
-
New models predict LLM accuracy using historical data, not self-assessment
Researchers have developed Generalized Correctness Models (GCMs) that can predict the accuracy of Large Language Models (LLMs) by learning from historical prediction patterns, rather than relying on the LLM's self-asses…
-
New Credal LLMs Improve Uncertainty Representation and Reduce Hallucinations
Researchers have introduced Credal Large Language Models (CLLMs) to address the issue of LLMs producing confident yet incorrect answers. Unlike standard LLMs that use a single predictive distribution, CLLMs employ an en…
-
New research probes RAG reliability, utility, and hallucination risks · 8 sources tracked
Recent research explores the nuances of Retrieval-Augmented Generation (RAG) systems, focusing on improving their reliability and utility. One paper details a system for the LLMs4OL 2026 Challenge that uses retrieval-au…
-
New audit method reveals hidden answer churn in retrieval-augmented QA systems
A new research paper introduces the Snapshot Compatibility Audit, a method to detect "accuracy-blind answer churn" in retrieval-augmented QA systems. This phenomenon occurs when system updates, such as index expansion, …
-
New methods tackle LLM and VLM hallucinations with internal analysis · 2 sources tracked
Researchers have developed new methods to detect hallucinations in large language and vision-language models. UniProbe, a technique for Large VLMs, uses a graph neural network, a Vision Transformer, and a gated recurren…
-
SmartRAG enables LLMs on mobile devices with graph-based RAG
Researchers have developed SmartRAG, a novel on-device framework designed to enable large language models (LLMs) to function as personal assistants on mobile devices. This system decomposes intelligence into four module…
-
J-space entropy shows mixed results as an error predictor in Qwen3-4B
A recent study explored using "J-space entropy," an internal metric within language models, to predict errors, particularly hallucinations. The research tested this hypothesis on the Qwen3-4B model across seven diverse …
-
New benchmark targets RAG systems against polymorphic sybil poisoning attacks
Researchers have developed a new benchmark and evaluation framework to assess retrieval-augmented generation (RAG) systems against polymorphic sybil poisoning attacks. This framework categorizes reader outputs into gold…