Pith. sign in

REVIEW 17 cited by

Internet-augmented language models through few-shot prompting for open-domain question answering

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2203.05115 v2 pith:FMSISGF2 submitted 2022-03-10 cs.CL cs.LG

Angeliki Lazaridou , Elena Gribovskaya , Wojciech Stokowiec , Nikolai Grigorev This is my paper
classification cs.CLcs.LG
keywords modelsfew-shotlanguageperformancepromptingansweringbettercompute
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

In this work, we aim to capitalize on the unique few-shot capabilities of large-scale language models (LSLMs) to overcome some of their challenges with respect to grounding to factual and up-to-date information. Motivated by semi-parametric language models (LMs), which ground their decisions in external retrieved evidence, we use few-shot prompting to learn to condition LMs on information returned from the web using Google Search, a broad and constantly updated knowledge source. Our approach does not involve fine-tuning or learning additional parameters, thus making it applicable to any LM, offering therefore a strong baseline. Indeed, we find that LMs conditioned on the web surpass performance of closed-book models of similar, or even larger, model sizes in open-domain question answering. Finally, we find that increasing the inference-time compute of models, achieved via using multiple retrieved evidences to generate multiple answers followed by a reranking stage that uses scores generated by the same LMs, leads to better performance and alleviates lower performance of smaller few-shot LMs. All in all, our findings suggest that it might be beneficial to slow down the race towards the biggest model and instead shift attention towards finding more effective ways to use models, including but not limited to, better prompting or increasing inference-time compute.

Discussion (0). Sign in to comment.

Forward citations

Cited by 17 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines

    cs.CL 2023-10 conditional novelty 8.0 of 10

    DSPy compiles short declarative programs into LM pipelines that self-optimize and outperform both standard few-shot prompting and expert-written chains on math, retrieval, and QA tasks.

  2. ROSE: Retrieval-Oriented Segmentation Enhancement

    cs.CV 2026-04 unverdicted novelty 7.0 of 10

    ROSE is a retrieval-augmented plug-in that improves MLLM segmentation on novel and emerging entities by fetching web text and images and deciding when to use them.

  3. From Standalone LLMs to Integrated Intelligence: A Survey of Compound Al Systems

    cs.MA 2025-06 accept novelty 7.0 of 10

    A survey that defines Compound AI Systems, proposes a multi-dimensional taxonomy based on component roles and orchestration strategies, reviews four foundational paradigms, and identifies key challenges for future research.

  4. LLM+P: Empowering Large Language Models with Optimal Planning Proficiency

    cs.AI 2023-04 accept novelty 7.0 of 10

    LLM+P lets LLMs solve planning problems optimally by converting them to PDDL for classical planners and back to natural language.

  5. MG$^2$-RAG: Multi-Granularity Graph for Multimodal Retrieval-Augmented Generation

    cs.IR 2026-04 conditional novelty 6.0 of 10

    A lightweight hierarchical multimodal graph RAG that fuses entity-grounded visual objects with text nodes and propagates relevance via multi-granularity PPR, delivering SOTA multimodal task performance at far lower co...

  6. MG$^2$-RAG: Multi-Granularity Graph for Multimodal Retrieval-Augmented Generation

    cs.IR 2026-04 unverdicted novelty 6.0 of 10

    MG²-RAG proposes a multi-granularity graph RAG framework that constructs hierarchical multimodal nodes via entity-driven visual grounding and performs structured retrieval, delivering SOTA results on four multimodal t...

  7. Retrieval-Augmented Generation for Natural Language Processing: A Survey

    cs.CL 2024-07 accept novelty 6.0 of 10

    The survey organizes RAG methods via a taxonomy of query-based, logits-based, latent, and parametric fusion with comparisons on accessibility, efficiency, applications, and challenges.

  8. Gorilla: Large Language Model Connected with Massive APIs

    cs.CL 2023-05 conditional novelty 6.0 of 10

    Gorilla is a fine-tuned LLM that surpasses GPT-4 in accurate API call generation and uses retrieval to handle documentation updates.

  9. ReWOO: Decoupling Reasoning from Observations for Efficient Augmented Language Models

    cs.CL 2023-05 conditional novelty 6.0 of 10

    ReWOO decouples reasoning from tool observations in augmented language models, delivering 5x token efficiency and 4% higher accuracy on multi-step reasoning benchmarks like HotpotQA.

  10. ART: Automatic multi-step reasoning and tool-use for large language models

    cs.CL 2023-03 unverdicted novelty 6.0 of 10

    ART automatically generates multi-step reasoning programs with tool integration for LLMs, yielding substantial gains over few-shot and auto-CoT prompting on BigBench and MMLU while matching hand-crafted CoT on most tasks.

  11. Atlas: Few-shot Learning with Retrieval Augmented Language Models

    cs.CL 2022-08 unverdicted novelty 6.0 of 10

    Atlas reaches over 42% accuracy on Natural Questions with only 64 examples, outperforming a 540B-parameter model by 3% with 50x fewer parameters.

  12. PRA-RAG: Provably Robust Aggregation in Retrieval-Augmented Generation against Retrieval Corruption

    cs.IR 2026-05 unverdicted novelty 5.0 of 10

    PRA-RAG is a new aggregation algorithm for RAG that claims provable robustness bounds against poisoned retrieved texts and reduces attack success rate to 1% while keeping 71% accuracy.

  13. Beyond Independent Passages: Adaptive Passage Combination Retrieval for Retrieval Augmented Open-Domain Question Answering

    cs.CL 2025-07 conditional novelty 5.0 of 10

    AdaPCR jointly retrieves and reranks passage pairs for open-domain QA, showing small EM/F1 gains over an in-context retrieval baseline, mostly on multi-hop HotpotQA.

  14. Capability-Aligned Hierarchical Learning for Tool-Augmented LLMs

    cs.AI 2026-06 unverdicted novelty 4.0 of 10

    CAHL jointly optimizes hierarchical policies for tool-augmented LLMs via RLVR and reports improved results on API-Bank, BFCL, and Bamboogle.

  15. Toward a Safe Internet of Agents

    cs.MA 2025-11 unverdicted novelty 4.0 of 10

    The paper proposes a bottom-up framework for safe agentic AI systems that treats each component as a dual-use interface where added capabilities also expand attack surfaces across single agents, multi-agent systems, a...

  16. BLUEX Revisited: Enhancing Benchmark Coverage with Automatic Captioning

    cs.CL 2025-08 conditional novelty 4.0 of 10

    An updated BLUEX benchmark with 1,422 questions and GPT-4o-generated captions that make image-based questions usable by text-only LLMs.

  17. A Comprehensive Overview of Large Language Models

    cs.CL 2023-07 unverdicted novelty 2.0 of 10

    A survey paper providing an overview of Large Language Models, their background, and recent advances in the field.

Pith tools