WildChat releases a dataset of 1 million ChatGPT conversations with timestamps, demographics, and headers, claimed to be the most diverse and multilingual such resource available.
hub Mixed citations
Dense Passage Retrieval for Open-Domain Question Answering
Mixed citation behavior. Most common role is background (64%).
94
Pith papers citing it
1,724
external citations · Crossref
Background
64% of classified citations
hub tools
citation-role summary
background 9
dataset 3
baseline 1
method 1
citation-polarity summary
co-cited works
representative citing papers
ORPO performs preference alignment during supervised fine-tuning via a monolithic odds ratio penalty, allowing 7B models to outperform larger state-of-the-art models on alignment benchmarks.
Mind2Web is the first large-scale dataset of real-world web tasks for developing generalist language-guided agents that complete complex actions on diverse websites.
SimCSE achieves 76.3% unsupervised and 81.6% supervised Spearman's correlation on STS tasks with BERT-base, improving prior best results by 4.2% and 2.2% via simple contrastive learning.
Tailored queries enable identification of the embedding model used by a black-box IR system from the unordered set of retrieved documents, even when a reranker is present.
A fixed-iteration spreading activation with per-step cosine similarity gating enables query-aware KG retrieval as one database query, matching QAFD-RAG on MuSiQue while cutting latency.
Retrieval coverage limits LLM rerankers in cold-start recommendation; a learned hybrid fusion improves pool quality but LLM reranking often degrades end-to-end performance while simpler rankers exploit the pool.
Introduces P-CHR AUC and CRR metrics to demonstrate that semantic caching model selection is limited by calibration quality rather than ranking performance.
DICE aggregates independently encoded document chunks into a single vector to reduce evidence dilution in long-document dense retrieval, reporting gains on LongEmbed especially beyond 4k tokens.
QCFuse achieves full-prefill quality in RAG with 1.7x average prefill speedup over full prefill and 1.5x over ProphetKV via compressed query-aware cache fusion.
Identifies the generative-discriminative gap in LLM hard negative synthesis for retrieval and proposes CausalNeg using CoT counterfactual perturbation plus query-view entropy maximization to generate more effective negatives.
MemPoison enables stealthy memory poisoning in LLM agents via dialogue by using semantic relational bridges, entity masquerading, and joint embedding optimization to bypass selective extraction and rewriting, achieving up to 0.95 attack success rate.
SilentRetrieval is a data poisoning attack achieving 84.6% HR@10 and 57.5% ASR-LLM on Natural Questions via coordinated beam search and trigger fusion while preserving document fluency.
Across 252,000 paired trials on six LLMs, topical relevance and list position emerged as the strongest drivers of first citation in competitive RAG, with price information and recency providing consistent secondary gains.
LLM-Wiki structures external knowledge as compilable wiki pages with links and persistent self-correction, achieving SOTA results on HotpotQA, MuSiQue, and 2WikiMultiHopQA by 2.0-8.1 F1 points over prior RAG systems.
IdioLink introduces a benchmark dataset and evaluation showing that strong embedding models struggle to retrieve equivalent meanings across idiomatic and literal forms, relying on shallow cues instead.
PluRule is a new multimodal multilingual benchmark showing that state-of-the-art vision-language models perform only marginally better than a trivial baseline at detecting specific rule violations in pluralistic online communities.
Semantic search retrieves substantially more implicit receptions of Locke's work than lexical baselines in 18th-century corpora, yet remains constrained by lexical gatekeeping.
ReaLM-Retrieve uses step-level uncertainty to trigger retrievals during reasoning, achieving 10.1% better F1 scores and 47% fewer calls on multi-hop QA benchmarks.
A product-key parametric memory head with selective sparse updates mitigates catastrophic forgetting in generative retrieval models during sequential addition of new documents.
LLM-based dense retrievers generalize better when instruction-tuned but pay a specialization tax when optimized for reasoning; they resist typos and corpus poisoning better than encoder-only baselines yet remain vulnerable to semantic perturbations, with larger models and certain embedding geometry,
A single model unifies retrieval and context compression for on-device RAG via shared representations, matching traditional RAG performance at 1/10 context size with no extra storage.
HiPRAG adds hierarchical process rewards to RL training for agentic RAG, reducing over-search to 2.3% and achieving 65.4-67.2% accuracy on seven QA benchmarks across 3B and 7B models.
Gemini 1.5 models achieve near-perfect recall over up to 10M tokens of multimodal context, improve long-document and long-video QA, and match or exceed prior Gemini 1.0 Ultra performance on standard benchmarks.
citing papers explorer
-
WildChat: 1M ChatGPT Interaction Logs in the Wild
WildChat releases a dataset of 1 million ChatGPT conversations with timestamps, demographics, and headers, claimed to be the most diverse and multilingual such resource available.
-
ORPO: Monolithic Preference Optimization without Reference Model
ORPO performs preference alignment during supervised fine-tuning via a monolithic odds ratio penalty, allowing 7B models to outperform larger state-of-the-art models on alignment benchmarks.
-
Mind2Web: Towards a Generalist Agent for the Web
Mind2Web is the first large-scale dataset of real-world web tasks for developing generalist language-guided agents that complete complex actions on diverse websites.
-
SimCSE: Simple Contrastive Learning of Sentence Embeddings
SimCSE achieves 76.3% unsupervised and 81.6% supervised Spearman's correlation on STS tasks with BERT-base, improving prior best results by 4.2% and 2.2% via simple contrastive learning.
-
Embedding Inference Attack
Tailored queries enable identification of the embedding model used by a black-box IR system from the unordered set of retrieved documents, even when a reranker is present.
-
Query-Aware Spreading Activation for Multi-Hop Retrieval over Knowledge Graphs
A fixed-iteration spreading activation with per-step cosine similarity gating enables query-aware KG retrieval as one database query, matching QAFD-RAG on MuSiQue while cutting latency.
-
Diagnosing and Mitigating Retrieval Bottlenecks in LLM-Based Cold-Start Recommendation
Retrieval coverage limits LLM rerankers in cold-start recommendation; a learned hybrid fusion improves pool quality but LLM reranking often degrades end-to-end performance while simpler rankers exploit the pool.
-
Closing the Calibration Gap in Semantic Caching
Introduces P-CHR AUC and CRR metrics to demonstrate that semantic caching model selection is limited by calibration quality rather than ranking performance.
-
Lost in a Single Vector: Improving Long-Document Retrieval with Chunk Evidence Aggregation
DICE aggregates independently encoded document chunks into a single vector to reduce evidence dilution in long-document dense retrieval, reporting gains on LongEmbed especially beyond 4k tokens.
-
QCFuse: Query-Aware Cache Fusion via Compressed View for Efficient RAG Serving
QCFuse achieves full-prefill quality in RAG with 1.7x average prefill speedup over full prefill and 1.5x over ProphetKV via compressed query-aware cache fusion.
-
When Hard Negatives Hurt: Bridging the Generative-Discriminative Gap in Hard Negative Synthesis for Retrieval
Identifies the generative-discriminative gap in LLM hard negative synthesis for retrieval and proposes CausalNeg using CoT counterfactual perturbation plus query-view entropy maximization to generate more effective negatives.
-
Hijacking Agent Memory: Stealthy Trojan Attacks Through Conversational Interaction
MemPoison enables stealthy memory poisoning in LLM agents via dialogue by using semantic relational bridges, entity masquerading, and joint embedding optimization to bypass selective extraction and rewriting, achieving up to 0.95 attack success rate.
-
SilentRetrieval: Hijacking Retrieval-Augmented Generation via Semantically-Preserving Adversarial Data Poisoning
SilentRetrieval is a data poisoning attack achieving 84.6% HR@10 and 57.5% ASR-LLM on Natural Questions via coordinated beam search and trigger fusion while preserving document fluency.
-
What Gets Cited: Competitive GEO in AI Answer Engines
Across 252,000 paired trials on six LLMs, topical relevance and list position emerged as the strongest drivers of first citation in competitive RAG, with price information and recency providing consistent secondary gains.
-
Retrieval as Reasoning: Self-Evolving Agent-Native Retrieval via LLM-Wiki
LLM-Wiki structures external knowledge as compilable wiki pages with links and persistent self-correction, achieving SOTA results on HotpotQA, MuSiQue, and 2WikiMultiHopQA by 2.0-8.1 F1 points over prior RAG systems.
-
IdioLink: Retrieving Meaning Beyond Words Across Idiomatic and Literal Expressions
IdioLink introduces a benchmark dataset and evaluation showing that strong embedding models struggle to retrieve equivalent meanings across idiomatic and literal forms, relying on shallow cues instead.
-
PluRule: A Benchmark for Moderating Pluralistic Communities on Social Media
PluRule is a new multimodal multilingual benchmark showing that state-of-the-art vision-language models perform only marginally better than a trivial baseline at detecting specific rule violations in pluralistic online communities.
-
Matching Meaning at Scale: Evaluating Semantic Search for 18th-Century Intellectual History through the Case of Locke
Semantic search retrieves substantially more implicit receptions of Locke's work than lexical baselines in 18th-century corpora, yet remains constrained by lexical gatekeeping.
-
When to Retrieve During Reasoning: Adaptive Retrieval for Large Reasoning Models
ReaLM-Retrieve uses step-level uncertainty to trigger retrievals during reasoning, achieving 10.1% better F1 scores and 47% fewer calls on multi-hop QA benchmarks.
-
A Parametric Memory Head for Continual Generative Retrieval
A product-key parametric memory head with selective sparse updates mitigates catastrophic forgetting in generative retrieval models during sequential addition of new documents.
-
On the Robustness of LLM-Based Dense Retrievers: A Systematic Analysis of Generalizability and Stability
LLM-based dense retrievers generalize better when instruction-tuned but pay a specialization tax when optimized for reasoning; they resist typos and corpus poisoning better than encoder-only baselines yet remain vulnerable to semantic perturbations, with larger models and certain embedding geometry,
-
A Unified Model and Document Representation for On-Device Retrieval-Augmented Generation
A single model unifies retrieval and context compression for on-device RAG via shared representations, matching traditional RAG performance at 1/10 context size with no extra storage.
-
HiPRAG: Hierarchical Process Rewards for Efficient Agentic Retrieval Augmented Generation
HiPRAG adds hierarchical process rewards to RL training for agentic RAG, reducing over-search to 2.3% and achieving 65.4-67.2% accuracy on seven QA benchmarks across 3B and 7B models.
-
Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context
Gemini 1.5 models achieve near-perfect recall over up to 10M tokens of multimodal context, improve long-document and long-video QA, and match or exceed prior Gemini 1.0 Ultra performance on standard benchmarks.
-
M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation
M3-Embedding is a single model for multi-lingual, multi-functional, and multi-granular text embeddings trained via self-knowledge distillation that achieves new state-of-the-art results on multilingual, cross-lingual, and long-document retrieval benchmarks.
-
Perhaps PTLMs Should Go to School -- A Task to Assess Open Book and Closed Book QA
Proposes a textbook-based true/false QA task where PTLMs score ~50% closed-book even after pre-training on the text and ~60% open-book with retrieval.
-
Relevance Is Not Permission: Warranted Attention for Value Contributions
Warrant adds a query-item permission gate g_ij to attention value terms, improving primary metrics in 27 of 32 comparisons across CTDG, MTPP, RAG, STPP, and TKG tasks.
-
MCompassRAG: Topic Metadata as a Semantic Compass for Paragraph-Level Retrieval
MCompassRAG adds topic metadata to chunk representations and uses LLM distillation to train a lightweight topic-aware retriever, reporting 8.24% average information efficiency gain and over 5x lower latency than strong baselines across six benchmarks.
-
SproutRAG: Attention-Guided Tree Search with Progressive Embeddings for Long-Document RAG
SproutRAG introduces an attention-guided hierarchical framework that constructs a binary chunking tree for multi-granularity retrieval in RAG systems and reports a 6.1% average gain in information efficiency.
-
Temporal Preference Optimization for Unsupervised Retrieval
TPOUR uses a novel TRPO method to improve unsupervised retrievers for temporal relevance, outperforming baselines including a much larger model on nDCG@5 for explicit and implicit time queries.
-
When Does Mixing Help? Analyzing Query Embedding Interpolation in Multilingual Dense Retrieval
Optimal interpolation of query embeddings from parallel translations outperforms the best monolingual query in 88/105 cases on mMARCO, showing English-driven asymmetry and negative correlation with typological distance.
-
STORM: Stepwise Token Optimization with Reward-Guided Beam Search
STORM trains lexical query rewriters via reward-guided beam search that converts retrieval metrics into stepwise token signals, enabling 0.6B-8B models to rival dense retrievers on TREC, BEIR and MIRACL without index changes.
-
HKVM-RAG: Key-Value-Separated Hypergraph Evidence Organization for Multi-Hop RAG
HKVM-RAG uses key-value-separated hypergraphs to organize LLM evidence tuples into answer-path hyperedges, yielding F1 gains over KG-PPR on two multi-hop QA benchmarks and further gains when combined with dense retrievers.
-
Boosting Self-Consistency with Ranking
RISC reformulates self-consistency answer selection as a ranking task solved by a lightweight LambdaRank model with five hand-designed features, yielding better accuracy-efficiency trade-offs than majority voting on QA benchmarks.
-
ANN Search: Recall What Matters
ANN search quality is better assessed by 1/Ratio@k than Recall@k because the former tracks downstream task utility more closely while allowing substantially lower computational cost.
-
When Retrieval Doesn't Help: A Large-Scale Study of Biomedical RAG
Large-scale evaluation shows retrieval-augmented generation yields only marginal and inconsistent gains (1-2 points) over no-retrieval baselines in biomedical QA, with model choice dominating retriever or corpus effects.
-
Learning When Not to Act: Mitigating Tool Abuse in Agentic Reinforcement Learning
EAPO learns selective tool use in agentic RL via tool-free trajectories, difficulty-aware reward shaping, and confidence-aware token reweighting, improving accuracy while cutting tool calls versus GRPO on nine reasoning benchmarks.
-
Beyond Topical Similarity: Contrastive Evidence Retrieval with Interpretable Attention Alignment in RAG
CERA fine-tunes a dense retriever with triplet contrastive learning plus attention alignment to human rationales, claiming better retrieval effectiveness and faithfulness on clinical trial reports than Contriever and standard hard-negative baselines.
-
More Context, Larger Models, or Moral Knowledge? A Systematic Study of Schwartz Value Detection in Political Texts
Context and retrieved moral knowledge improve sentence-level Schwartz value detection more consistently than model scaling, with early-fusion RAG outperforming other variants in matched comparisons.
-
Proof-Carrying Certificates for LLM Pipelines: A Trust-Boundary Architecture
Introduces a trust-boundary architecture in Lean 4 with three certificate families and two operators that deliver sorry-free, axiom-audited assurances for LLM pipeline components.
-
REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinations
REALISTA generates semantically coherent adversarial prompts via latent-space optimization over input-dependent editing directions, achieving stronger hallucination elicitation than prior realistic attacks on open-source and reasoning LLMs.
-
The Interference Gap: Comparing Retrieval Bounds in Human Memory and RAG Systems
Unified SDT model finds humans less sensitive to interference (α/σ=0.41) than dense passage retrieval (0.67), with HippoRAG intermediate (0.44), backed by N=112 experiments and simulations favoring logarithmic over power-law decline.
-
OBLIQ-Bench: Exposing Overlooked Bottlenecks in Modern Retrievers with Latent and Implicit Queries
OBLIQ-Bench demonstrates that modern retrievers fail to surface most documents relevant to latent and implicit queries, while reasoning LLMs can reliably recognize relevance when documents are provided.
-
Kernel Affine Hull Machines as Compute-Efficient Encoders for Frozen Semantic Spaces
KAHM yields a compute-efficient query encoder that outperforms matched learned adapters in reconstructing a frozen Mixedbread embedding space on an Austrian-law retrieval task while delivering an 8.53x CPU speedup.
-
A Replicability Study of XTR
XTR training does not improve retrieval effectiveness over ColBERT but enhances IVF engine efficiency by flattening token scores to produce more discriminative centroids.
-
InvEvolve: Evolving White-Box Inventory Policies via Large Language Models with Performance Guarantees
InvEvolve evolves inventory policies using LLMs with RL and provides statistical safety guarantees, outperforming classical and DL methods on synthetic and real data.
-
Learning to Route Queries to Heads for Attention-based Re-ranking with Large Language Models
RouteHead trains a lightweight router to dynamically select optimal LLM attention heads per query for improved attention-based document re-ranking.
-
Where and What: Reasoning Dynamic and Implicit Preferences in Situated Conversational Recommendation
SiPeR improves recommendation accuracy and response quality in situated conversations by estimating scene transitions and performing Bayesian inverse inference with multimodal LLMs.
-
Adaptive Defense Orchestration for RAG: A Sentinel-Strategist Architecture against Multi-Vector Attacks
A context-aware Sentinel-Strategist system for RAG selectively applies defenses to block membership inference and data poisoning while recovering most retrieval utility compared to always-on defense stacks.
-
R$^3$AG: Retriever Routing for Retrieval-Augmented Generation
R³AG routes queries to retrievers by decomposing capabilities into retrieval quality and generation utility, trained via contrastive learning on document assessments and downstream answer correctness to outperform static methods.