Dissertations - M Tech (CS)

Permanent URI for this collectionhttp://164.52.219.250:4000/handle/10263/2147

These Dissertations were submitted in partial fulfilment of the requirements for the award of M TECH (Computer Science) Degree of Indian Statistical Institute

Browse

Filters

20251

Settings

Author: search.filters.author.Chatterjee, SandeepSubject: search.filters.subject.Large Language Models

Search Results

Now showing 1 - 1 of 1
  • No Thumbnail Available
    Item
    Efficient Blending of Large Language Models
    (Indian Statistical Institute, Kolkata, 2025-06) Chatterjee, Sandeep
    Due tothelimitedcapabilitiesofsingleLargeLanguageModels(LLMs),multipleLLMscanbe employedintandemforbetterreliabilityofanswers.Blendingreferstocombiningthestrengths of variousLLMstomakeuseoftheircomplementarycapabilitiesforgeneratinghigh-quality responses.Itisanon-trivialproblem,andthetaskbecomesevenmoredifficultwhenaiming for minimallatencyandsupervisingtheblendingcomponents.Thestandardframework,LLM- Blender, approachesthisinthreestages:responsegeneration,candidateselectionviaranking, and responsefusionthroughsummarization.However,thispipelinefacestwocriticallimita- tions—high latencyduetorepeatedrankingsteps,andheavyrelianceonexternal,supervised componentsincludingalearnedencoderforrankingandaseparatesequence-to-sequencesum- marizer forfusion. In thisthesis,weproposenovel,efficientalternativestoovercomethesechallenges.Thisthesis comprises twoworks.First,weshowthatreducingthefrequencyofrankingwithinmulti- turn conversationssignificantlyimproveslatencywithminimaldegradationinoutputquality. Second, weintroduceapeer-review-basedresponsefusionmechanism,whereLLMscollectively evaluateandreviseeachother’sresponses,removingtheneedforanyexternallytrainedrankers or summarizers.Thiscollaborativemethodenablesfullyself-containedLLMblendingwithout additional trainingorsupervision. WeassessourproposedmethodsonthetaskofConversationalQuestionAnsweringacrossfive multi-turnconversationalbenchmarks—ConvQuestions,Atlas-Converse,CoQA,QuAC,and DoQA—using tendiverse,publiclyavailableopen-weightLLMs.Experimentalresultsdemon- strate thatourpeer-review-drivenframeworkwithreducedrankingachievesqualityonparwith existing approacheswhilebeingsubstantiallymoreefficient.Ourworkpresentsasteptoward scalable, modularLLMensemblingforreal-worldopen-domaindialoguesystems.